Global visibility in compute content rendering systems and applications

Abstract

The proposed method provides a camera-independent computation of the global visibility of the surface geometry of a multidimensional model. The model can be positioned relative to a voxel mesh, and a colorimetric operation is performed to identify cells that fall within the region accessible to the virtual camera but do not intersect with the surface geometry. Individual elements of the surface geometry allow for the selection of sample points, and a determination of whether any of the sample points of a given element is within the maximum permissible distance of a cell or portion of the camera-accessible region. If so, another determination is made regarding whether an unobstructed path exists between any of the sample points of the element and the camera-accessible region. If such a path exists, the element is labeled as visible and considered when rendering an image of the model. Otherwise, the element is labeled as invisible and excluded from consideration during rendering.

Description

[0001] Cross-reference to related applications This application claims priority to U.S. nonprovisional patent application No. 19 / 013,492, filed January 8, 2025, entitled “CALCULATING GLOBAL VISIBILITY INCONTENT RENDERING SYSTEMS AND APPLICATIONS,” the entire contents of which are incorporated herein by reference for all purposes. Background Technology

[0002] In various applications, such as those for gaming, animation, or virtual reality content generation, it is beneficial (if not necessary) to represent complex 3D objects and / or scenes in a manner that is substantially accurate or at least consistent, even for large or complex scenes or environments. Rendering processes can be used to generate images of complex 3D models from the viewpoint of a virtual camera. As part of the rendering process, it is necessary to determine the visibility of various elements or surface geometries of the model relative to the virtual camera. Various algorithms and methods have been developed to determine the camera-dependent visibility of these elements. For example, ray tracing processes may handle camera-dependent visibility by considering the order in which rays intersect surfaces in the scene. This approach requires preprocessing the data for fast and efficient ray-scene intersection calculations, and this preprocessing can be complex and expensive. Furthermore, this process only determines camera-dependent visibility, meaning that visibility determination often needs to be repeated for different camera positions, which further increases resource costs and overhead when creating multiple views, such as for video or augmented reality content. Attached Figure Description

[0003] Various embodiments according to this disclosure will be described with reference to the accompanying drawings, in which: Figure 1A and Figure 1B An example view of an object model including a camera-accessible area and a camera-inaccessible area is shown according to at least one embodiment; Figure 2A and Figure 2B A view of an object model positioned relative to a cell grid according to at least one embodiment is shown, which can be used to determine the camera-accessible area and to track the path from the surface geometry to the camera-accessible area; Figure 3A and Figure 3B An example algorithm for identifying air cells and invisible elements according to at least one embodiment is shown; Figure 3C Sample points selected for triangular elements of a surface geometry according to at least one embodiment are shown; Figure 4 An example process for calculating global visibility according to at least one embodiment is shown; Figure 5A and Figure 5B Components of an example content generation system according to at least one embodiment are shown; Figure 6 Components of a distributed system, according to at least one embodiment, are shown that can be used to generate and provide image content using object and scene models; Figure 7A The inference and / or training logic according to at least one embodiment is illustrated; Figure 7B The inference and / or training logic according to at least one embodiment is illustrated; Figure 8 An example data center system according to at least one embodiment is shown; Figure 9 A computer system according to at least one embodiment is shown; Figure 10 A computer system according to at least one embodiment is shown; Figure 11 At least a portion of a graphics processor according to one or more embodiments is shown; Figure 12 At least a portion of a graphics processor according to one or more embodiments is shown; Figure 13 This is an example data flow diagram of an advanced computing pipeline according to at least one embodiment; Figure 14 This is a system diagram of an example system for training, adapting, instantiating, and deploying machine learning models in an advanced computing pipeline, according to at least one embodiment; and Figure 15A and Figure 15B A data flow diagram of the process for training a machine learning model according to at least one embodiment is shown, as well as a client-server architecture for enhancing annotation tools using a pre-trained annotation model. Detailed Implementation

[0004] In the following description, various embodiments will be described. Specific configurations and details are set forth for illustrative purposes in order to provide a thorough understanding of the embodiments. However, it will also be apparent to those skilled in the art that the embodiments can be practiced without specific details. Furthermore, well-known features may be omitted or simplified so as not to obscure the described embodiments.

[0005] The systems and methods described herein can be used by, but are not limited to, non-autonomous vehicles or machines, semi-autonomous or autonomous vehicles or machines (e.g., in one or more advanced driver assistance systems (ADAS), one or more in-vehicle infotainment systems, one or more emergency vehicle detection systems), manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, aircraft, ships, space shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, airplanes, engineering vehicles, trains, underwater vehicles, remotely operated vehicles (such as drones), and / or other vehicle types. Furthermore, the systems and methods described herein can be used for a variety of purposes, as examples and not limitations, including: machine control, machine movement, machine actuation, synthetic data generation, generative AI, model training, perception, augmented reality, virtual reality, mixed reality, robotics, security and supervision, simulation and digital twinning, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, data center processing, conversational AI, optical transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation for 3D assets, generative AI, cloud computing, and / or any other suitable applications.

[0006] The disclosed embodiments may be included in a variety of different systems, such as automotive systems (e.g., in-vehicle infotainment systems for autonomous or semi-autonomous machines, perception systems for autonomous or semi-autonomous machines), systems implemented using robots, aviation systems, medical systems, rowing systems, smart area monitoring systems, systems for performing deep learning operations, systems for performing simulation operations, systems for performing digital twin operations, systems implemented using edge devices, systems combining one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least partially in a data center, systems for performing conversational AI operations, systems implementing one or more language models (such as large language models (LLMs) or visual language models (VLMs), etc.), systems for performing generative AI operations (e.g., using one or more language models, transformer models, etc.), systems for performing optical transmission simulations, systems for performing collaborative content creation for 3D assets, systems implemented at least partially using cloud computing resources, and / or other types of systems.

[0007] In some examples, one or more machine learning models described herein (e.g., deep neural networks, language models, LLMs, VLMs, multimodal language models, perceptual models, tracking models, fusion models, transformer models, diffusion models, encoder-only models, decoder-only models, encoder-decoder models, neural rendering field (NERF) models, etc.) can be packaged as microservices—such as inference microservices (e.g., NVIDIA NIM)—that may include containers (e.g., operating system (OS) level virtualization packages) that may include an application programming interface (API) layer, a server layer, a runtime layer, and / or at least one model “engine.” For example, an inference microservice may include the container itself and one or more models (e.g., weights and biases). In some cases, such as when one or more machine learning models are sufficiently small (e.g., have a sufficiently small number of parameters), one or more models may be included within the container itself. In other examples—such as when one or more models are large—the models may be hosted / stored in the cloud (e.g., in a data center) and / or may be hosted on-premises and / or deployed at the edge (e.g., on a local server or compute device, but outside the container). In such embodiments, one or more models may be accessible via one or more APIs, such as a REST API. Thus, and in some embodiments, the machine learning models described herein can be deployed as inference microservices to accelerate the deployment of one or more models on any cloud, data center, or edge computing system while ensuring data security. For example, an inference microservice may include one or more APIs, pre-configured containers for simplified deployment, an optimized inference engine (e.g., using standardized AI model deployment execution software such as NVIDIA's Triton Inference Server), and / or one or more APIs for high-performance deep learning inference, which may include inference runtimes and model optimizations for delivering low latency and high throughput to production applications—such as NVIDIA's TensorRT), and / or enterprise management data for telemetry (e.g., including identity, metrics, health checks, and / or monitoring).

[0008] One or more machine learning models described herein can be included as part of a microservice along with an acceleration infrastructure capable of deployment using a single command and / or orchestration and autoscaling (e.g., on a single device up to data center scale) using a container orchestration system on the acceleration infrastructure. Thus, the inference microservice can include one or more machine learning models (e.g., models already optimized for high-performance inference), inference runtime software for executing one or more machine learning models and providing outputs / responses to inputs (e.g., user queries, prompts, etc.), and enterprise management software for providing health checks, identity, and / or other monitoring. In some embodiments, the inference microservice can include software for performing in-situ replacement and / or updates to one or more machine learning models. During replacement or update, the software performing the replacement / update can maintain user configurations for the inference runtime software and the enterprise management software.

[0009] The methods according to various illustrative embodiments provide for identifying portions or elements of complex models (e.g., 3D models of objects or scenes) that are invisible to any camera placed outside the surface geometry of the model and therefore might be ignored during operations such as ray tracing (or other light transport simulation techniques) and rendering. The model can be positioned relative to a mesh having cell spacing *s*, where the cell mesh (e.g., a voxel mesh) can be considered the background of the object model, and the mesh cells are cubes (e.g., voxels) with faces having lateral dimensions *s*. Mesh cells determined to contain surface geometry (e.g., at least a triangle or at least a portion of a face of a mesh, or at least a portion of the surface of at least one object model for a scene) can be labeled as geometric cells. An outer layer of cells can be added around the outer edge of the mesh, wherein all of these outer cells are indicated as excluding the surface geometry of the model. This outer layer then consists entirely of cells that are entirely camera-accessible. This camera-accessible region of the cells can be grown or expanded by indicating that any mesh cell adjacent to one of these camera-accessible cells that does not contain any surface geometry is also a camera-accessible cell. The camera-accessible area of ​​a cell can be expanded until no more undefined mesh cells are adjacent to a camera-accessible cell that does not intersect with at least a certain amount of object geometry. Any remaining undefined cells that do not contain surface geometry can be defined as unreachable, at least for a camera positioned anywhere within the camera-accessible area. To identify visible elements of geometry, only camera-accessible cells are considered. A gap size threshold can be set such that slits or gaps in the surface geometry smaller than the gap size threshold are considered closed (or otherwise not gaps through which an unobstructed path can be traced or through which the camera-accessible area can be expanded).

[0010] Initially, all elements corresponding to cells not included in the camera's visible area can be marked as invisible. If there exists at least one straight line connecting an element to any camera-visible cell or other portion of the camera-visible area, where the line must not intersect any other element of the surface geometry, then elements of the surface geometry (such as triangles of a mesh) can be updated to visible. To make the computation feasible, only rays, lines, or paths from multiple sample points on the individual elements are considered. Thus, an instance or element of the surface geometry (e.g., a triangle or face) can have multiple identified sample points with spacing that can correspond to a cell size selected by the user. Rays or paths can be projected from these sample points to any camera-visible cell within a given distance. If at least one ray or path is found connecting a sample point and a camera-visible cell, and this ray does not intersect any other element of the geometry, then the element can be marked as visible or camera-visible (among other such options). Otherwise, the element is marked as invisible or camera-inaccessible. Since elements are invisible to the camera anywhere within the camera's visible area, elements marked or designated as invisible can be excluded from use or consideration in the rendering pipeline or process. This cell-based approach takes a continuously sampled problem and makes it a discrete problem that is solvable with significantly less time and resource capacity.

[0011] As will be apparent to those skilled in the art from the teachings and suggestions contained herein, this functionality and other variations thereof may also be used within the scope of various embodiments.

[0012] For example, when rendering a 2D image of a 3D (or 4D, etc.) object, a virtual camera is positioned relative to the digital 3D model, and the image can be generated based on the virtual camera's position, orientation, and parameters. Many digital 3D models (such as CAD models of complex objects like cars or buildings) will contain elements of surface geometry that are not visible from any camera position and would not require passing through opaque elements to be accessible. For example, a digital model of a vehicle might include a complex model of the vehicle's engine, but the virtual camera would be inaccessible to the engine unless the car's hood is open (which may or may not be possible). Similarly, pipes may exist in the walls of a building represented in a 3D model, but typically, a virtual camera would not be allowed to pass through the walls to allow the generation of images of the pipes during regular rendering. The visibility of a car's interior, such as that which may include seats and a steering wheel, can depend on whether windows are considered (at least partially) transparent or opaque. Considering geometry invisible to the virtual camera (at least in its current state) could result in significant memory and processing usage, which would not affect the image generated for this model. Being able to ignore or remove such invisible geometry from consideration can significantly improve rendering speed and reduce resource requirements for generating images that are partly based on this model.

[0013] The method according to at least one embodiment allows for the identification of “invisible” or inaccessible surface geometry in a digital model (3D or otherwise). This identification can be performed at various levels, such as at the level of the entire mesh, the connected portions of the mesh, or individual faces, and other such options. In at least one embodiment, the method also allows approximate visibility to be calculated by specifying a gap size threshold. The use of a gap size threshold can be important because meshes representing objects such as cars typically contain narrow slits, gaps, or openings between features. In this case, a large portion of the mesh used for rendering, which can be omitted according to the precise definition of visibility, is visible. As mentioned above, complex digital objects such as buildings, cars, airplanes, or robots are most commonly designed or modeled using CAD-based systems. CAD models are highly detailed descriptions of objects that typically contain thousands of individual parts. For example, for the visualization of a car or a virtual walk through a building, a large number of these parts would no longer be visible to any camera that does not pass through the opaque surface.

[0014] As an example, in Figure 1A A vehicle model 102 is shown in a cross-sectional view 100. Although shown in a 2D cross-section and discussed in terms of two dimensions, it should be understood that a 3D (or 4D, etc.) model may also be used, including 3D meshes, sampling, and path determination according to various embodiments. Figure 1AIn this rendering, the vehicle model has opaque surface portions (such as the hood, truck, roof, and tires) and transparent surface portions (such as the windshield and rear window). In various rendering scenarios, the virtual camera 104 can be used as a guide for rendering one or more views of the vehicle from different positions and / or orientations of the virtual camera 104, including various parameter values ​​of the virtual camera related to scaling level, aspect ratio, etc. The virtual camera 104 can be located at any position 104(a) outside the vehicle, such as representing the outdoors outside the vehicle. In this example, because the vehicle model includes transparent (or at least partially transparent or translucent) surface portions, the virtual camera 104 can also be positioned at various positions 104(b) inside the vehicle's cabin, or at least objects or surfaces within the cabin that can be viewed through transparent surfaces. Therefore, it is desirable to maintain the surfaces inside the cabin for consideration during the rendering process for realism and detail, where at least a portion of these surfaces can be partially visible based on the position and orientation of the virtual camera 104.

[0015] However, other parts of model 102 (e.g., faces or surfaces) may exist that are not visible to such a virtual camera. For example, in the engine compartment under the hood, there may be various engine parts 108 that are not visible through the opaque hood unless it is opened. Therefore, at least in the current state of the model, there may not be a way to position the virtual camera to make the engine parts 108 visible. Modeling modern engines can be very complex, with many fine details, and if these engine parts are not visible in the rendered image anyway, a reasonable amount of work may be needed to preserve these parts for tasks such as hit testing during ray tracing. Similarly, in the trunk, there may be packages 106, spare tires, emergency toolboxes, or other objects that are not visible at least in the current state of vehicle model 102, where the opaque trunk lid is closed and the interior is inaccessible to the virtual camera. It should be understood that in some rendering operations, the camera may be placed separately or intentionally in the engine compartment, trunk, or other such areas, but for other operations, such access will be prevented unless the state of the model is modified to make those areas accessible.

[0016] Identifying areas or parts of the model that are "invisible" or inaccessible to the virtual camera in the image to be used for rendering the model can be helpful. (See also: Regarding...) Figure 1A As discussed in model 102, this could involve identifying the engine compartment area 152 and the trunk area 154 (or similar front and rear areas) as inaccessible or containing invisible surface geometries, such as... Figure 1BThe cross-sectional view 150 is shown. Once determined, the surface geometry of these regions 152, 154 can be excluded from consideration during rendering or other such processing. The ability to exclude these surface geometry portions from consideration reduces the amount of memory required to store the model geometry to be considered during the rendering process. Furthermore, reducing the amount of surface geometry allows for less computation to be performed during tasks such as ray tracing, which reduces the amount of resources required and also reduces the amount of time required to perform rendering operations, thereby providing reduced latency and increased efficiency for the rendering pipeline and / or computing system.

[0017] The method according to at least one embodiment can identify "invisible" or inaccessible objects, faces, or other surface geometries and remove them from the scene, or at least remove them from consideration for the scene. When analyzing global visibility or camera-independent visibility, if and only if there exists a distance from outside the scene or model to point p ∈ f When a path does not intersect any opaque geometry of the model, a face (or mesh or other part of the model) can be considered visible. However, for real-world objects, this precise definition of visibility may not be entirely applicable because small gaps often exist between individual meshes. Sometimes the mesh itself contains faces that are not precisely aligned. Therefore, visibility can be computed in a more robust manner on a regular background mesh with user-defined spacing. Using such a mesh not only improves robustness but also allows for an efficient way to determine visibility. The effectiveness of this approach has been observed using various real-world data.

[0018] Figure 2AA cross-sectional view 200 of a 3D model of a vehicle superimposed on a rectangular mesh is shown. As shown, there will be a number of mesh cells 204 that intersect with opaque surfaces, edges, or faces of the 3D model. These intersecting cells 204, or cells that overlap with opaque geometry, are shown as white cells. If a cell overlaps or intersects with any part of the surface geometry, the cell can be labeled as an intersecting cell, regardless of how small the cell is. Starting from a point outside the model, there will be a number of cells 202 that are accessible to the virtual camera and will therefore be referred to herein as the camera-accessible region. These cells are shown in a dark pattern. In at least one embodiment, the virtual camera may be allowed to move freely within the camera-accessible region, as long as the camera does not pass through any opaque surface geometry. The cells of this camera-accessible region can be considered as “air” cells, or cells in which portions of nearby geometry can be rendered for one or more viewpoints of the virtual camera. In addition, there will be some cells 206 that do not intersect or overlap with opaque geometry and are also inaccessible from the air cells without passing through the opaque geometry. In various rendering methods, the geometry within these invisible units 206 is invisible in any rendered image because the virtual camera cannot be manipulated to a visible location without passing through the opaque geometry (which is not allowed in at least some implementations) or without intentionally placing the virtual camera in that location. It should be understood that flood fill can also begin from other areas, such as the engine compartment area (if the virtual camera will be placed (or can be placed) within this area).

[0019] exist Figure 2AIn the examples, a regular background mesh with a defined mesh spacing s can be used. This spacing can be defined by a user, operator, process, or other authorized entity or source. In at least one embodiment, the size of such a mesh can be selected such that the mesh contains the entire geometry in the scene and has an additional cell boundary around the edges of the mesh that does not intersect or overlap with the object geometry. In at least one embodiment, the initial analysis of such a mesh can be performed in three dimensions (or more dimensions), although the example is provided in two dimensions. In one such method, any cell contained in the outer padding layer can be designated as an “air” cell (or a accessible cell, etc.). Any cell containing, intersecting with, or overlapping any amount (or at least a threshold amount) of opaque geometry can be labeled as an “opaque” cell. Any other cell can initially be labeled as an “empty” cell. Empty cells can be analyzed to determine whether these empty cells are adjacent to at least one air cell without any interpolated or intermediate opaque cells. If so, each such empty cell can also be labeled, tagged, or otherwise designated or considered as an air cell or a cell within the camera's accessible area. This method effectively utilizes air cells to fill mesh diffuses to a degree that allows reaching cells without traversing at least one opaque cell. In this example, the diffuse starts outside the scene or model and stops at an opaque cell in the mesh. Volumes surrounded by opaque cells and inaccessible to the diffuse can be left as empty cells. This method can be parallelized, allowing diffuses to be filled more quickly by concurrently applying diffuses to multiple cells along multiple paths. The union of air cells then provides an approximation of the space through which a virtual camera can traverse without passing through opaque geometry.

[0020] Using this method, the definition of camera-independent visibility can be reformulated to consider the possibility that there exists a point from inside an air cell to point p ∈ f When the path does not intersect with any opaque geometry, the face... f It is visible. It can be noted that, given... Figure 3A In the case of the definition of an air cell in the first algorithm 300 shown, this new formulation is equivalent to the previous definition of visibility. Up to this point in the discussion, using a grid has not introduced any approximations. However, instead of finding an open path from a point all the way to the outside of the scene, it is now sufficient to find an open path to adjacent air cells. To improve robustness and speed, the definition can be slightly modified for a grid-based, camera-independent definition of visibility. In such a definition, visibility is defined if and only if there exists a path from a point inside an air cell to a point p ∈ f A shape that does not intersect with any opaque geometry and has a length When the path is, face fIt is evident. This definition may be beneficial because it allows for the consideration of fewer visible faces. For example, for a car with tinted windows, if the tinted loop in the first algorithm 300 does not pass through the gaps around the doors, the interior of the car will not be filled with air cells, and the interior geometry will be too far from the set of air cells to be considered visible.

[0021] This method only allows testing paths to adjacent mesh cells, not paths from outside the scene (or model, etc.). p All possible paths are considered. However, even with this approach, a large number of potential paths still need to be considered. To further reduce the number of paths to consider, and to make this approach more practical and efficient for implementation, at least a certain amount of path sampling can be performed. Several different latent sampling algorithms can be used, which can further reduce the number of visible points by generating false negatives. In at least one embodiment, this can be achieved by marking points as invisible, even if these points are visible based on the definition of mesh-based, camera-independent visibility, since sampling does not consider all possible paths. The number of false negatives depends at least in part on the selected sampling density. The sensitivity to these false negatives can depend in part on the granularity of the output. In at least one embodiment, the user can choose between several (e.g., three) different types of granularity. The type of granularity can include, for example, face-based visibility, island-based visibility, and mesh-based visibility. In this context, an island can refer to the largest set of faces connected via common vertices. An island or mesh (or other such construction) can be defined as visible if it contains at least one face that is determined to be visible. In this case, incorrectly classifying a subset of faces as invisible does not change the result. Figure 3B A second algorithm 330 is shown that can be used to identify whether point p is visible, thus providing a visibility check of point p and normal n. The first part of this algorithm primarily divides the cells into those that are fully or partially camera-reachable. Cells containing surface geometry can still allow light to pass through so that the geometry is visible from the camera-reachable area, but a conservative colorimetric approach helps to quickly narrow down the possible camera angles and positions for testing. A limited number of samples of the surface geometry can be performed, partly based on the location of the camera-reachable area. This example algorithm 350 only checks the path from p to the nearest point in the union of adjacent air cells. With this selection, only a single segment-scene intersection test needs to be performed for each point. For fast intersection testing, a bounding volume hierarchy containing a boundary for each face in the scene can be used. To ensure that the path being tested does not point to a surface, only those air cells that are in front of p relative to the normal n are considered.

[0022] Back Figure 2AThe diagram shows three sample points corresponding to three different scenarios. Inside the carriage, there exists a first sample point 210 with a path to the nearest point in the air unit that does not intersect with any surface geometry, making point 210 visible. The second sample point 212 also has adjacent air units nearby, but the path to this point 212 is blocked by surface geometry, making sample point 212 invisible. The third sample point 214 is too far from any air unit and can also be marked as invisible.

[0023] Figure 2B It shows Figure 2A A partial view 250 of the model's cross-section. To determine the visibility of each face, the surface is sampled using various test points. Initially, all faces and vertices to be tested are marked as invisible. In the first loop of the example method, all vertices are tested for visibility using vertex normals. All faces adjacent to visible vertices are also set to visible. Figure 2B In the sample, there exist first sample points 256 that are identified as visible because they have connecting lines 258 or paths to sufficiently close air (or camera-accessible) cells 252, where connecting lines 258 or paths do not intersect the surface geometry. There will still exist some vertices, such as point 260, that are still marked as invisible because no suitable path to a nearby air cell has yet been identified, or a potential path 262 does not reach a visible cell. Invisible cells 254 may also be marked as invisible.

[0024] In at least one embodiment, a maximum path length can be set to determine whether the camera-accessible area is sufficiently close to a given sample point. There may be a large number of air cells within the camera-accessible area, but when viewing the path of the air cells, it is sufficient to view the air cells near the sample point, because if there is no unobstructed path to the sample point from closer air cells along a given direction, then air cells farther away in that given direction will not allow the sample point to be visible. The length can be set to further reduce processing requirements and time while still achieving a reasonable approximation. In at least one embodiment, the maximum path distance is twice the cell size. If there are no air cells or portions of the camera-accessible area within the maximum path distance to the sample point, a path test for that sample point can be completed without performing path tracing. This method provides an early stopping condition that can further help reduce the total processing time for visibility determination.

[0025] In at least one embodiment, the second loop of this algorithm can involve testing all faces that are still marked as invisible. Visibility testing of these faces can be performed by selecting and testing a set of sample points 364 on face 360, such as... Figure 3CAs shown. In this example, the face can conceptually be divided into a set of triangles, which can then be sampled individually. The distance can be determined on the longest side. s 1. This distance is less than s The maximum distance that evenly divides the edge. The distance can be determined. s 2. This distance is the distance between the second longer side and the equal number of segments. These two distances can be used to create a set of sampling lines 362. This can be used... s i (i.e., less than) s The maximum distance at which the lines are uniformly divided creates one or more sampling points 364 on each of these lines. Triangle normals can be used for the sampling points. In at least one embodiment, the surface sampling distance can be selected to be equal to the grid spacing, while in another embodiment, the sampling distance can be set to half the grid spacing, and other such options. However, since this distance is independent of the grid spacing, it can be disclosed as a second input parameter whose value can be modified by the user or other authorized source. Visibility testing can be performed on each of these sampling points, and if any of the sampling points for a triangle or face is determined to be visible, the entire triangle or face can be considered visible and retained for rendering considerations. As mentioned, in at least one embodiment, visibility testing is performed on a portion of an air cell or camera-accessible area within a given neighborhood or proximity, in part according to the maximum path distance setting. It can be determined whether any air cells exist within the maximum path distance of the sampling points, and if so, whether a path between the sampling points and the air cells that does not intersect the surface geometry can be identified. If such a path can be identified, then this sample point (and its corresponding triangle, face, or element) can be identified or updated to have a visible setting or label.

[0026] As mentioned, the visibility of certain components can be based in part on the determined gap size. One can imagine a log cabin made of stacked logs, where small gaps or gaps may exist between the logs. In at least one embodiment, any furniture in the cabin can be considered globally visible due to these gaps or gaps in the walls. However, if the grid spacing is set to be larger than the gap or gap size, air cells will not enter the interior of the cabin, and the furniture can be considered invisible. If the cell size is reduced to be smaller than the gap size, air cells can diffuse into the interior of the cabin, making the furniture visible. For example, in a video game, this could allow a character to see the interior of the cabin by looking through the gaps between the logs. Therefore, it can be shown that cell size can be determined by balancing efficiency and detail, as larger cell sizes would make furniture invisible and thus excluded from consideration during the rendering process, which could provide faster rendering but with less fine detail.

[0027] A graph-like structure can also be used to represent how different parts of a 3D scene are interconnected based on visibility. This structure can highlight key visibility events, such as occlusion, where one object blocks the view of another. This structure can be used in various applications, including shadow casting, global illumination, and hidden surface determination. However, instead of relying on this complex data structure, methods according to various embodiments can be as follows: Figure 2A The diagram shows a simple regular hexahedral mesh. Global visibility is equivalent to finding an unobstructed path from an object to a point outside the scene. Sampling the scene and color-coding open cells (or voxels) allows for the efficient identification of large subsets of globally visible locations. Working with voxels also allows these and other such methods to handle arbitrary meshes or even trianglesoups, and other such constructions.

[0028] Figure 4An example process 400, which can be executed according to at least one embodiment, to calculate the global visibility of elements of at least one model for an object or scene. It should be understood that, with respect to these and other processes presented herein, within the scope of various embodiments, unless specifically stated otherwise, additional, fewer, or alternative steps may exist, executed in a similar or alternative order, or at least partially in parallel. Furthermore, although this example will be discussed with regard to a 3D object model, other types of models having other types of surface geometry may also be used within the scope of various embodiments. In this example process 400, there is at least one object model as part of a scene for which one or more images are to be rendered. To facilitate rendering from any of multiple different viewpoints of a virtual camera, global visibility can be calculated for individual elements of the model's surface geometry. To calculate global visibility, the object model can be aligned 402 with a virtual mesh comprising a plurality of cells. This may include, for example, where the cells have... s The 3D mesh consists of voxel cells of a side dimension. In at least one embodiment, it can be ensured that there is at least one outer cell layer of the mesh that does not include the surface geometry of the model and is outside the surface geometry of the model. The edge cells of this virtual mesh 404 can be selected as cells of the camera-accessible region. As mentioned, there can be areas of cells through which the virtual camera can pass or positioned relative to the model. If there are transparent geometric portions with openings in the geometry, the camera-accessible region may also pass through into a portion of the object model. In at least one embodiment, a gap size threshold can be set such that any gap or opening smaller than this threshold is not considered a gap or opening through which the camera can pass. The camera-accessible region 406 can be extended to include adjacent mesh cells that do not contain any of the surface geometry or need to pass through cells that include some of the surface geometry.

[0029] Once the extent of the camera-accessible region has been determined, this region can be used to test the visibility of elements of the surface geometry. In this example process 400, individual elements of the model's surface geometry are set 408 to "invisible" elements, or elements invisible to a camera positioned within the camera-accessible region. At least some of these elements can be analyzed to determine whether these elements (and any potentially adjacent elements) are actually visible to a camera within the camera-accessible region. In this example process, a set of sample points can be determined for various elements, and an attempt can be made to determine whether at least one unobstructed path exists between a given sample point and the camera-accessible region. For example, this could include a straight path of up to a maximum length that does not intersect any surface geometry before reaching the camera-accessible region. At least one such unobstructed path can be updated 410 for those elements of the surface geometry to which it is identified to be labeled or designated as visible elements. In some embodiments, at least some nearby elements may also be labeled as visible elements. When rendering an image of the object model from a given viewpoint of a virtual camera, visible elements can be preserved and taken into account. During at least one subsequent rendering of an image using a virtual camera positioned within the camera's visible area, the remaining invisible elements of the surface geometry can be excluded from consideration. The advantage of this camera-independent global visibility is that this visibility indicator and a set of visible surface geometries can be reused at several different camera positions to render images of several different views of the object model without recalculating or verifying visibility, which can improve speed and efficiency compared to existing rendering methods.

[0030] If the scene model is used only for rendering, removing (or ignoring) invisible geometry (which may involve millions of elements, such as triangles in a mesh) can significantly improve rendering speed. The method disclosed herein can identify invisible geometry at the level of the entire mesh, the connected portion of the mesh, or individual faces, and other such options. Approximate visibility calculations can be performed by specifying a gap size threshold, since meshes used for objects such as vehicles typically contain narrow gaps or gaps between elements (as well as overlapping elements and other incomplete data). In this case, most of the meshes used for rendering that can be omitted, according to the precise definition of visibility, are visible. This approach allows for the handling of real-world data that is often imperfect at the mesh and face levels, and even low-quality inputs that may relate to assemblies of triangles. In at least one embodiment, only one parameter (e.g., mesh size or density) needs to be specified for the visibility calculation algorithm, although a gap size threshold or other such parameters may also be specified in various cases. For example, a small mesh size can allow the air cell color diffusion process to slip through very small gaps, while a larger mesh size will prevent the color diffusion process from passing through small gaps between meshes or elements, etc.

[0031] Another advantage of this approach is that many operations can be performed in parallel. For example, iterative color filling by analyzing neighboring pixels can be performed concurrently from multiple pixels. Similarly, path testing of sample points, and other such operations, can be performed in parallel. The ability to run these operations in parallel can significantly reduce the amount of time required to perform global visualization computations, especially when using one or more processors, such as graphics processing units (GPUs), which are highly efficient at performing parallel operations and also allow for hardware acceleration. The ability to parallelize operations is also beneficial when used with huge meshes that can have hundreds of millions of other instances of triangles, meshes, or surface geometries, especially when using GPUs capable of handling such a large number of parallel operations.

[0032] As mentioned, a virtual camera can be used to determine a view of one or more object or scene models for which its image (or other representation) is to be rendered or otherwise generated. Figure 5A Example virtual environment 500 for rendering such images, video frames, or image-related content according to at least one embodiment is shown. Such a system may include or incorporate functionality as presented herein to allow for a portion of an unobstructed visual path to a camera-accessible area, taking into account the surface geometry of the model, and other such options. In this example, an image will be rendered for a scene within virtual environment 500, although such a system could also be used to render images for semi-virtual or real environments. Virtual environment 500 may include geometry and other data representing shapes or objects within the environment, such as three-dimensional (3D) objects representing scenes occurring within the environment or to be included in scenes occurring within the environment, which may include foreground objects such as people or vehicles, or background objects such as roads and buildings, and other such options. In at least some embodiments, at least some of the content for the scene may also be obtained from resource repository 502 or other such locations, which may contain content that can be used to render the scene, such as geometry, texture, and density data. In at least some embodiments or instances, a user device 504 may be present running a content generation or management application that allows the user to select at least relevant portions of assets 502 and virtual environment 500 for scene rendering. User device 504 may also allow the user to control aspects of the image to be rendered, such as the position or pose of objects in the scene, and the viewpoint and other parameters of the virtual camera used to render the image of virtual environment 500. Once rendered, the image may be stored in image storage 522 and / or provided to a user or display device 524 for presentation, among other options.

[0033] In this example, at least one computing resource 506 is used to perform rendering. This resource may correspond to one or more servers, which may be located locally or span at least one network, among other such options. In some embodiments, rendering may alternatively be performed at least partially on user device 504. Computing resource 506 may acquire or receive data to be used for rendering, which may include geometry, texture, and density data for a virtual environment or asset, as well as information about the position and pose of those objects in the scene and parameters of a virtual camera to be used to determine the view of the scene to be rendered. This information may, for example, be received by a content application 508, which may execute on the central processing unit (CPU) 510 of the computing resource, which is responsible for tasks such as collecting data, rendering images, and performing any formatting or encoding of the resulting images, among other such operations. Content applications may work with, for example, a rendering manager 512, which may be responsible for coordinating the operations of a rendering pipeline executed on computing resource 506. This rendering manager may include modules 514, 516, or processes responsible for tasks such as geometry-related tasks (including lighting and shading tasks) and rasterization, among others. In at least one embodiment, rendering manager 512 may use at least one NeRF-based model as discussed herein to generate a digital reconstruction of virtual environment 500. In at least some embodiments, at least some of these rendering tasks may be executed using one or more GPUs 520A-D and potentially one or more processors or computing instances (physical or virtual) of computing resources.

[0034] Tasks such as optical transport simulation (e.g., ray tracing, path tracing, ray travel, etc.) or volumetric sampling can be performed using a single processor, such as a single GPU, or can have operations distributed across multiple GPUs 520A-D. In this example, a pool or set of GPUs 520A-D may exist, and the resource manager 518 may be at least partially responsible for allocating GPUs to perform the processing for the operation. If using more than one GPU is desired or beneficial, the resource manager 518 may allocate one or more GPUs with appropriate capacity or capability. This may include multiple GPUs indicated in the allocation request, or determining the multiple GPUs to allocate in part based on the request. In some embodiments, the resource manager may also be able to monitor available bandwidth or memory to determine which GPUs to allocate and how many GPUs to allocate, such as in cases where high bandwidth capacity allows operations to be distributed across a larger number of GPUs (where the bandwidth impact due to forwarding ray information will be less critical), while in bandwidth-constrained systems the resource manager may attempt to allocate as few GPUs as possible to try to reduce the number of forwarded messages required.

[0035] In at least one embodiment, for example, data partitioning can be performed by the rendering manager 512, and data assignment to different processors can be performed by the system's resource manager 518. The resource manager can receive information from the rendering component and can select an appropriate processor from the pool of available processors 520 or processor capacity. In some embodiments, the rendering application can choose the partitioning, while in other embodiments, the renderer may not have control over data partitioning, which can be handled by a separate management component (…). Figure 5A (Not shown in the image) to complete.

[0036] Figure 5B An example image generation pipeline 550 is shown, which can be used in a virtual environment 500—such as... Figure 5AThe virtual environment shown is for rendering one or more images, such as video frames in a sequence for a specific scene and / or domain. In this example, pixel data 552 for the current frame to be rendered (which may include G-buffer data for the main surface) can be received as input to the reflection and refraction component 554 of the rendering system. The reflection and refraction component 554 can use this data to attempt to determine any determined reflection and / or refraction data for the pixel data, and can provide this data to a backprojection and G-buffer patching component 556, which can perform backpropagation as discussed herein to locate corresponding points for these reflections and refractions, and use this data to patch a G-buffer 568, which can provide updated input for subsequent frames to be rendered. The data can then be provided to a light sample generation component 558 for performing light sampling, a ray tracing lighting component 560 for performing ray tracing lighting, and one or more shaders 562, which can set the pixel colors for various pixels of the frame based at least in part on the determined lighting information (and other information such as color, texture, etc.). The results can be accumulated by the accumulation module 564 or components to generate an output frame 566 of the desired size, resolution, or format.

[0037] In at least one embodiment, shader 562 can perform a backprojection step. Once the backprojection pass has been completed and the gradient surface parameters have been patched into the current G-buffer, the renderer can perform a lighting pass. Using information from the lighting pass and the lighting results from the previous frame, gradients can be computed, and these gradients are then filtered and used for history rejection. This approach can be used to compute robust temporal gradients between the current and previous frames in the temporal denoising unit of a ray-tracing renderer. This backprojection-based approach can also work with reflection and refraction and can work with a rasterized G-buffer. Previous methods for backprojection omit any G-buffer patching and instead rely on the original current G-buffer samples, which also leads to false positive gradients. Patching the surface parameters can eliminate false positives in most cases, making the denoised image very stable yet still responsive to changes in illumination. Once the backprojection pass has been completed and the gradient surface parameters have been patched into the current G-buffer, the renderer can perform a lighting pass. Using information from the lighting pass and the lighting results from the previous frame, gradients are computed, and these gradients are then filtered and used for history rejection. NeRF or other machine learning models can be used at various stages of this pipeline for use in all aspects of the inference rendering process.

[0038] The various methods presented herein are lightweight enough to be executed in real time in a variety of locations, such as on client devices including personal computers or game consoles. This processing can be performed on or for content generated on or received by or from an external source on this client device (such as streaming data or other content received via at least one network from a cloud server 620 or a third-party service 660, and other such options). In some cases, the processing, generation, composition, and / or determination of at least a portion of this content can be performed by one of these other devices, systems, or entities and then provided to the client device (or another such receiver) for presentation or another such purpose.

[0039] As an example, Figure 6An example network configuration 600 is shown that can be used to provide, generate, modify, encode, process, and / or send image data or other such content. In at least one embodiment, client device 602 can use components of content application 604 on client device 602 and data locally stored on this client device to generate or receive data for a session. In at least one embodiment, content application 624 executing on server 620 (e.g., cloud server or edge server) can initiate a session associated with at least one client device 602 that can utilize a session manager and user data stored in user database 636, and can cause content such as one or more digital assets (e.g., implicit and / or explicit object representations, such as models or meshes) from asset repository 634 to be determined by content manager 626. Content manager 626 can work with rendering module 628 to generate or select objects, digital assets, or other such content to be represented in an image to be rendered. Views of these objects can be rendered by rendering module 628 and provided via client device 602 for presentation. In at least one embodiment, the rendering module 628 may work in conjunction with a visibility calculator 630, which analyzes sample points on a surface to identify visible and invisible surface geometry, allowing the rendering module 628 to exclude invisible geometry from consideration when rendering an image. The content application may include a training module 632 that trains one or more generative networks, such as those used to generate or process content, or perform other such operations, wherein those models may be trained or fine-tuned for a specific scene, domain, or other such aspect. In at least one embodiment, a machine learning model may be used to infer the global visibility of surface geometry elements, wherein this machine learning model is trained based on the methods presented herein. At least a portion of the rendered and composite (or otherwise generated or selected) content may be transmitted to the client device 602 via download, streaming, or another such transmission channel using a suitable transmission manager 622. An encoder may be used to encode and / or compress at least some of this data before transmission to the client device 602. In at least one embodiment, a client device 602 receiving such content may provide the content to a corresponding content application 604, which may also or alternatively include a graphical user interface 610, a content manager 612, and a rendering module 614 for providing, composing, rendering, combining, modifying, or using the content for presentation (or for other purposes) on or by the client device 602.The decoder can also be used to decode data received via one or more networks 640 for presentation via client device 602, such as image or video content via display 606 and audio such as sound and music via at least one audio playback device 608 (such as a speaker or headphones). In at least one embodiment, at least some of this content may already be stored on, rendered on, or accessible by client device 602, such that at least this portion of the content does not need to be transmitted via network 640, such as in cases where the content may have been pre-downloaded or stored locally on a hard drive or optical disc. In at least one embodiment, a transmission mechanism such as data streaming can be used to transmit this content from server 620 or user database 636 to client device 602. In at least one embodiment, at least a portion of this content may be obtained, enhanced, and / or streamed from another source, such as third-party service 660 or other client device 650, which may also include content application 662 for generating, enhancing, or providing content. In at least one embodiment, this functional part can be performed using multiple computing devices or multiple processors (such as a combination of CPU and GPU) within one or more computing devices.

[0040] In this example, these client devices can include any suitable computing device, such as desktop computers, laptops, set-top boxes, streaming devices, game consoles, smartphones, tablets, VR headsets, AR goggles, wearable computers, or smart TVs. Each client device can submit requests via at least one wired or wireless network, which can include the Internet, Ethernet, a local area network (LAN), or a cellular network, among other such options. In this example, these requests can be submitted to an address associated with a cloud provider that operates or controls one or more electronic resources within a cloud provider environment, such as a data center or server cluster. In at least one embodiment, the request can be received or processed by at least one edge server located at the network edge and outside at least one security layer associated with the cloud provider environment. In this way, latency can be reduced by enabling client devices to interact with servers in closer proximity, while also improving the security of resources within the cloud provider environment.

[0041] In at least one embodiment, such a system can be used to perform graphics rendering operations. In other embodiments, such a system can be used for other purposes, such as providing image or video content to test or validate autonomous machine applications, or for performing deep learning operations. In at least one embodiment, such a system can be implemented using edge devices, or can be combined with one or more virtual machines (VMs). In at least one embodiment, such a system can be implemented at least partially in a data center or at least partially using cloud computing resources.

[0042] Reasoning and training logic Figure 7A Inference and / or training logic 715 is shown for performing inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7B Provide details about reasoning and / or training logic 715.

[0043] In at least one embodiment, inference and / or training logic 715 may include, but is not limited to, code and / or data storage 701 for storing forward and / or output weights and / or input / output data, and / or other parameters configuring neurons or layers of a neural network trained for and / or used for inference in one or more embodiments. In at least one embodiment, training logic 715 may include or be coupled to code and / or data storage 701 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic, including integer and / or floating-point units (collectively, arithmetic logic units (ALUs)). In at least one embodiment, code (such as graph code) loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, code and / or data storage 701 stores weight parameters and / or input / output data of each layer of a neural network trained or used in one or more embodiments during forward propagation of input / output data and / or weight parameters during training and / or inference using one or more embodiments. In at least one embodiment, any portion of the code and / or data storage 701 may be included within other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0044] In at least one embodiment, any portion of the code and / or data storage 701 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 701 may be a cache memory, dynamic random access memory (“DRAM”), static random access memory (“SRAM”), non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice of whether the code and / or data storage 701 is internal or external to the processor, for example, or composed of DRAM, SRAM, flash memory, or some other storage type, may depend on the available on-chip or off-chip storage space, the latency requirements of the training and / or inference functions being performed, the batch size of the data used in the inference and / or training of the neural network, or some combination of these factors.

[0045] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, code and / or data storage 705 for storing backpropagation and / or output weights and / or input / output data corresponding to neurons or layers of a neural network trained and / or used for inference in one or more embodiments. In at least one embodiment, during training and / or inference using one or more embodiments, the code and / or data storage 705 stores weight parameters and / or input / output data for each layer of a neural network trained or used in one or more embodiments during backpropagation of input / output data and / or weight parameters. In at least one embodiment, the training logic 715 may include or be coupled to code and / or data storage 705 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic including integer and / or floating-point units (collectively, an arithmetic logic unit (ALU)). In at least one embodiment, code (such as graph code) loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, any portion of the code and / or data storage 705 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. In at least one embodiment, any portion of the code and / or data storage 705 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 705 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice between the code and / or data storage 705 being internal or external to the processor, for example, whether it consists of DRAM, SRAM, flash memory, or some other type of storage, depends on whether the available storage is on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the data batch size used in the inference and / or training of the neural network, or some combination of these factors.

[0046] In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be separate storage structures. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be the same storage structure. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be partially identical and partially separate storage structures. In at least one embodiment, any portion of code and / or data storage 701 and code and / or data storage 705 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0047] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, one or more arithmetic logic units (“ALUs”) 710 (including integer and / or floating-point units) for performing logical and / or mathematical operations at least in part based on or instructed by training and / or inference code (e.g., graph code), the results of which may produce activations (e.g., output values ​​from layers or neurons within a neural network) stored in activation storage 720, which are functions of input / output and / or weight parameter data stored in code and / or data storage 701 and / or code and / or data storage 705. In at least one embodiment, activation is activated in response to execution instructions or other code, and linear algebraic and / or matrix-based mathematical generation performed by ALU 710 is stored in activation storage 720, wherein weight values ​​stored in code and / or data storage 705 and / or code and / or data storage 701 are used as operands with other values, such as bias values, gradient information, momentum values, or other parameters or hyperparameters, and any or all of these can be stored in code and / or data storage 705 or code and / or data storage 701 or other on-chip or off-chip storage.

[0048] In at least one embodiment, one or more processors or other hardware logic devices or circuits include one or more ALUs 710, while in another embodiment, one or more ALUs 710 may be located outside the processor or other hardware logic device or the circuitry using them (e.g., a coprocessor). In at least one embodiment, one or more ALUs 710 may be included within an execution unit of a processor, or otherwise included in a group of ALUs accessible by the execution unit of the processor, which may be within the same processor or distributed among different processors of different types (e.g., a central processing unit, a graphics processing unit, a fixed-function unit, etc.). In at least one embodiment, code and / or data storage 701, code and / or data storage 705, and activation storage 720 may be on the same processor or other hardware logic device or circuitry, while in another embodiment, they may be on different processors or other hardware logic devices or circuitries, or in some combination of the same and different processors or other hardware logic devices or circuitries. In at least one embodiment, any portion of activation storage 720 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Furthermore, inference and / or training code may be stored together with other code accessible to the processor or other hardware logic or circuitry, and may be retrieved and / or processed using the processor’s fetch, decode, schedule, execute, exit, and / or other logic circuitry.

[0049] In at least one embodiment, the active memory 720 may be a cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other memory. In at least one embodiment, the active memory 720 may be wholly or partially located inside or outside one or more processors or other logic circuits. In at least one embodiment, the choice of whether the active memory 720 is internal to or external to the processor may depend on the available on-chip or off-chip storage, the latency requirements for training and / or inference functions, the batch size of data used in inference and / or training the neural network, or some combination of these factors. For example, it may include DRAM, SRAM, flash memory, or other memory types. In at least one embodiment, Figure 7A The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (“ASIC”), such as a Tensorflow® processing unit from Google, an inference processing unit (IPU) from Graphcore™, or a Nervana® (e.g., “LakeCrest”) processor from Intel Corp. In at least one embodiment, Figure 7A The inference and / or training logic 715 shown can be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware such as field programmable gate array (“FPGA”).

[0050] Figure 7B Inference and / or training logic 715 according to at least one or more embodiments is illustrated. In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, hardware logic, wherein computational resources are dedicated or otherwise uniquely used in conjunction with weight values ​​or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, Figure 7B The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (ASIC), such as a TensorFlow® processing unit from Google, an inference processing unit (IPU) from Graphcore™, or a Nervana® (e.g., “LakeCrest”) processor from Intel Corp. In at least one embodiment, Figure 7B The inference and / or training logic 715 shown can be used in conjunction with central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or other hardware (e.g., field-programmable gate array (FPGA)). In at least one embodiment, the inference and / or training logic 715 includes, but is not limited to, code and / or data storage 701 and code and / or data storage 705, which can be used to store code (e.g., graph code), weight values, and / or other information, including bias values, gradient information, momentum values, and / or other parameter or hyperparameter information. Figure 7B In at least one embodiment shown, each of code and / or data storage 701 and code and / or data storage 705 is associated with dedicated computing resources (e.g., computing hardware 702 and computing hardware 706), respectively. In at least one embodiment, each of computing hardware 702 and computing hardware 706 includes one or more ALUs that perform mathematical functions (e.g., linear algebraic functions) only on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, and the results of the function execution are stored in activation storage 720.

[0051] In at least one embodiment, each of the code and / or data storage 701 and 705 and the corresponding computing hardware 702 and 706 corresponds to a different layer of the neural network, such that activation obtained from one “store / computation pair 701 / 702” of the code and / or data storage 701 and computing hardware 702 provides input as input to the next “store / computation pair 705 / 706” of the code and / or data storage 705 and computing hardware 706, in order to reflect the conceptual organization of the neural network. In at least one embodiment, each store / computation pair 701 / 702 and 705 / 706 may correspond to more than one neural network layer. In at least one embodiment, additional store / computation pairs (not shown) may be included in the inference and / or training logic 715 after or in parallel with the store / computation pairs 701 / 702 and 705 / 706.

[0052] Data Center Figure 8 An example data center 800 that can be used with at least one embodiment is shown. In at least one embodiment, the data center 800 includes a data center infrastructure layer 810, a framework layer 820, a software layer 830, and an application layer 840.

[0053] In at least one embodiment, such as Figure 8As shown, the data center infrastructure layer 810 may include a resource coordinator 812, grouped computing resources 814, and node computing resources (“nodes CR”) 816(1)-816(N), where “N” represents any positive integer. In at least one embodiment, nodes CR 816(1)-816(N) may include, but are not limited to, any number of central processing units (“CPUs”) or other processors (including accelerators, field-programmable gate arrays (FPGAs), graphics processors, etc.), memory devices (e.g., dynamic read-only memory), storage devices (e.g., solid-state drives or disk drives), network input / output (“NWI / O”) devices, network switches, virtual machines (“VMs”), power modules, and cooling modules, etc. In at least one embodiment, one or more nodes CR 816(1)-816(N) may be servers having one or more of the aforementioned computing resources.

[0054] In at least one embodiment, the grouped computing resources 814 may include individual groups (not shown) of node CRs housed in one or more racks, or a plurality of racks (also not shown) housed in data centers in various geographic locations. Individual groups of node CRs within the grouped computing resources 814 may include computing, networking, memory, or storage resources that can be configured or allocated to support groups of one or more workloads. In at least one embodiment, several node CRs, including CPUs or processors, may be grouped within one or more racks to provide computing resources to support one or more workloads. In at least one embodiment, one or more racks may also include any number of power modules, cooling modules, and network switches, in any combination.

[0055] In at least one embodiment, resource coordinator 812 may be configured or otherwise control one or more nodes CR816(1)-816(N) and / or grouped computing resources 814. In at least one embodiment, resource coordinator 812 may include a Software Design Infrastructure (“SDI”) management entity for data center 800. In at least one embodiment, resource coordinator 108 may include hardware, software, or some combination thereof.

[0056] In at least one embodiment, such as Figure 8As shown, framework layer 820 includes a job scheduler 822, a configuration manager 824, a resource manager 826, and a distributed file system 828. In at least one embodiment, framework layer 820 may include a framework of software 832 supporting software layer 830 and / or one or more applications 842 supporting application layer 840. In at least one embodiment, software 832 or application 842 may respectively include web-based service software or applications, such as services or applications provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, framework layer 820 may be, but is not limited to, a free and open-source software web application framework, such as Apache Spark™ (hereinafter referred to as "Spark") which can leverage distributed file system 828 for large-scale data processing (e.g., "big data"). In at least one embodiment, job scheduler 832 may include Spark drivers to facilitate the scheduling of workloads supported by the various layers of data center 800. In at least one embodiment, configuration manager 824 may be able to configure different layers, such as software layer 830 and framework layer 820 including Spark and distributed file system 828 for supporting large-scale data processing. In at least one embodiment, resource manager 826 is capable of managing cluster or group computing resources mapped to or allocated to support distributed file system 828 and job scheduler 822. In at least one embodiment, cluster or group computing resources may include group computing resources 814 on data center infrastructure layer 810. In at least one embodiment, resource manager 826 may coordinate with resource coordinator 812 to manage these mapped or allocated computing resources.

[0057] In at least one embodiment, the software 832 included in the software layer 830 may include software used by at least a portion of the nodes CR816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. One or more types of software may include, but are not limited to, Internet web page search software, email virus scanning software, database software, and streaming video content software.

[0058] In at least one embodiment, one or more applications 842 included in application layer 840 may include one or more types of applications used by at least a portion of nodes CR816(1)-816(N), grouped computing resources 814, and / or the distributed file system 828 of framework layer 820. One or more types of applications may include, but are not limited to, any number of genomics applications, cognitive computing and machine learning applications, including training or inference software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in conjunction with one or more embodiments.

[0059] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource coordinator 812 can perform any number and type of self-modification actions based on any amount and type of data acquired in any technically feasible manner. In at least one embodiment, self-modification actions can mitigate potentially poor configuration decisions by data center operators of data center 800 and can prevent underutilization and / or poor performance of the data center.

[0060] In at least one embodiment, data center 800 may include tools, services, software, or other resources to train one or more machine learning models or to use one or more machine learning models to predict or infer information according to one or more embodiments described herein. For example, in at least one embodiment, a machine learning model can be trained by calculating weight parameters based on a neural network architecture using the software and computing resources described above with respect to data center 800. In at least one embodiment, information can be inferred or predicted using trained machine learning models corresponding to one or more neural networks using the resources described above with respect to data center 800 by using weight parameters calculated through one or more training techniques described herein.

[0061] In at least one embodiment, the data center may use a CPU, application-specific integrated circuit (ASIC), GPU, FPGA, or other hardware to utilize the aforementioned resources to perform training and / or inference. Furthermore, one or more of the aforementioned software and / or hardware resources may be configured as a service to allow a user to train or perform information inference, such as image recognition, speech recognition, or other artificial intelligence services.

[0062] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. This document combines... Figure 7A and / or Figure 7BDetails are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be implemented in the system. Figure 8 Used in systems for reasoning or predicting operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0063] Such components can be used to calculate camera-independent global visibility of elements of an object or scene model that will be used to generate images from the viewpoint of a virtual camera.

[0064] Computer System Figure 9 This is a block diagram illustrating an exemplary computer system according to at least one embodiment. The exemplary computer system may be a system with interconnected devices and components, a system-on-a-chip (SoC), or some combination thereof formed with a processor, which may include an execution unit to execute instructions. In at least one embodiment, according to this disclosure, such as the embodiments described herein, computer system 900 may include, but is not limited to, components such as processor 902, whose execution unit includes logic to execute algorithms for process data. In at least one embodiment, computer system 900 may include a processor, such as the PENTIUM® processor family, Xeon™, Itanium®, XScale™ and / or StrongARM™, Intel® Core™ or Intel® Nervana™ microprocessors available from Intel Corporation of Santa Clara, California, although other systems (including PCs, engineering workstations, set-top boxes, etc.) with other microprocessors may also be used. In at least one embodiment, the computer system 900 may execute a version of the Windows operating system available from Microsoft Corporation of Redmond, Washington, although other operating systems (such as UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0065] The embodiments can be used in other devices, such as handheld devices and embedded applications. Some examples of handheld devices include cellular phones, Internet Protocol (IP) devices, digital cameras, personal digital assistants (“PDAs”), and handheld PCs. In at least one embodiment, the embedded application may include a microcontroller, a digital signal processor (“DSP”), a system-on-a-chip (SoC), a network computer (“NetPC”), a set-top box, a network hub, a wide area network (“WAN”) switch, or any other system that can execute one or more instructions according to at least one embodiment.

[0066] In at least one embodiment, the computer system 900 may include, but is not limited to, a processor 902, which may include, but is not limited to, one or more execution units 908, to perform machine learning model training and / or inference according to the techniques described herein. In at least one embodiment, the computer system 900 is a single-processor desktop or server system, but in another embodiment, the computer system 900 may be a multiprocessor system. In at least one embodiment, the processor 902 may include, but is not limited to, a Complex Instruction Set Computing (“CISC”) microprocessor, a Reduced Instruction Set Computing (“RISC”) microprocessor, a Very Long Instruction Word (“VLIW”) computing microprocessor, a processor implementing instruction set combination, or any other processor device, such as a digital signal processor. In at least one embodiment, the processor 902 may be coupled to a processor bus 910, which can transmit data signals between the processor 902 and other components in the computer system 900.

[0067] In at least one embodiment, processor 902 may include, but is not limited to, a Level 1 (“L1”) internal cache memory (“cache”) 904. In at least one embodiment, processor 902 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory may reside external to processor 902. Depending on specific implementation and requirements, other embodiments may also include a combination of internal and external caches. In at least one embodiment, register file 906 may store different types of data in various registers, including but not limited to integer registers, floating-point registers, status registers, and instruction pointer registers.

[0068] In at least one embodiment, a logic execution unit 908, including but not limited to performing integer and floating-point operations, is also located within the processor 902. In at least one embodiment, the processor 902 may further include a microcode (“ucode”) read-only memory (“ROM”) for storing microcode of certain macro instructions. In at least one embodiment, the execution unit 908 may include logic for processing a packaged instruction set 909. In at least one embodiment, by including the packaged instruction set 909 in the instruction set of a general-purpose processor, along with the associated circuitry for executing the instructions, the packaged data in the processor 902 can be used to perform operations used by numerous multimedia applications. In one or more embodiments, the execution of numerous multimedia applications can be accelerated and performed more efficiently by using the full width of the processor’s data bus to perform operations on the packaged data, which may eliminate the need to transfer smaller data units on the processor’s data bus to perform one or more operations on one data element at a time.

[0069] In at least one embodiment, execution unit 908 may also be used in a microcontroller, embedded processor, graphics device, DSP, and other types of logic circuitry. In at least one embodiment, computer system 900 may include, but is not limited to, memory 920. In at least one embodiment, memory 920 may be implemented as a dynamic random access memory (“DRAM”) device, a static random access memory (“SRAM”) device, a flash memory device, or other storage device. In at least one embodiment, memory 920 may store instructions 919 and / or data 921 represented by data signals that can be executed by processor 902.

[0070] In at least one embodiment, the system logic chip may be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip may include, but is not limited to, a memory controller hub (“MCH”) 916, and the processor 902 may communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 may provide a high-bandwidth memory path 918 to the memory 920 for instruction and data storage, as well as for storage of graphics commands, data, and textures. In at least one embodiment, the MCH 916 may initiate data signals between the processor 902, the memory 920, and other components in the computer system 900, and bridge data signals between the processor bus 910, the memory 920, and the system I / O 922. In at least one embodiment, the system logic chip may provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 may be coupled to the memory 920 via the high-bandwidth memory path 918, and the graphics / video card 912 may be coupled to the MCH 916 via an Accelerated Graphics Port (“AGP”) interconnect 914.

[0071] In at least one embodiment, computer system 900 may use system I / O 922, which is a proprietary hub interface bus, to couple MCH 916 to I / O controller hub (“ICH”) 930. In at least one embodiment, ICH 930 may provide direct connectivity to certain I / O devices via a local I / O bus. In at least one embodiment, the local I / O bus may include, but is not limited to, a high-speed I / O bus for connecting peripheral devices to memory 920, chipset, and processor 902. Examples may include, but are not limited to, audio controller 929, firmware hub (“FlashBIOS”) 928, wireless transceiver 926, data storage 924, a conventional I / O controller 923 including user input and keyboard interfaces, serial expansion port 927 (e.g., a Universal Serial Bus (USB) port), and network controller 934. Data storage 924 may include hard disk drives, floppy disk drives, CD-ROM devices, flash memory devices, or other mass storage devices.

[0072] In at least one embodiment, Figure 9 A system including interconnected hardware devices or "chips" is shown, while in other embodiments, Figure 9An exemplary system-on-a-chip (SoC) may be illustrated. In at least one embodiment, the device may be interconnected with a proprietary interconnect, a standardized interconnect (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of the computer system 900 are interconnected using a compute fast link (CXL) interconnect.

[0073] The inference and / or training logic 715 is used to perform inference and / or training operations related to one or more embodiments. (The following is in conjunction with...) Figure 7A and / or Figure 7B Details are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be... Figure 9 Used in systems for reasoning or predicting operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0074] Such components can be used to calculate camera-independent global visibility of elements of an object or scene model that will be used to generate images from the viewpoint of a virtual camera.

[0075] Figure 10 This is a block diagram illustrating an electronic device 1000 for utilizing a processor 1010 according to at least one embodiment. In at least one embodiment, the electronic device 1000 may be, for example, but not limited to, a laptop computer, tower server, rack server, blade server, desktop computer, tablet computer, mobile device, telephone, embedded computer, or any other suitable electronic device.

[0076] In at least one embodiment, the electronic device 1000 may, but is not limited to, a processor 1010 communicatively coupled to any suitable number or type of components, peripherals, modules, or devices. In at least one embodiment, the processor 1010 uses a bus or interface coupling, such as an I°C bus, a system management bus (“SMBus”), a low pin count (LPC) bus, a serial peripheral interface (“SPI”), a high-definition audio (“HDA”) bus, a serial advanced technology accessory (“SATA”) bus, a universal serial bus (“USB”) (versions 1, 2, and 3), or a universal asynchronous receiver / transmitter (“UART”) bus. In at least one embodiment, Figure 10 The system shown includes interconnected hardware devices or "chips," while in other embodiments, Figure 10 An exemplary system-on-a-chip (SoC) can be illustrated. In at least one embodiment, Figure 10 The device shown can be interconnected with proprietary interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, Figure 10One or more components are interconnected using Computational Fast Link (CXL) interconnects.

[0077] In at least one embodiment, Figure 10 This may include a display 1024, a touchscreen 1025, a touchpad 1030, a near-field communication unit (“NFC”) 1045, a sensor hub 1040, a thermal sensor 1046, a fast chipset (“EC”) 1035, a trusted platform module (“TPM”) 1038, a BIOS / firmware / flash (“BIOS, FWFlash”) 1022, a DSP 1060, a drive 1020 (e.g., a solid-state drive (“SSD”) or a hard disk drive (“HDD”)), a wireless local area network unit (“WLAN”) 1050, a Bluetooth unit 1052, a wireless wide area network unit (“WWAN”) 1056, a global positioning system (GPS) 1055, a camera (“USB 3.0 camera”) 1054 (e.g., a USB 3.0 camera), and / or a low-power double data rate (“LPDDR”) memory unit (“LPDDR3”) 1015 implemented in, for example, the LPDDR3 standard. These components may each be implemented in any suitable manner.

[0078] In at least one embodiment, other components may be communicatively coupled to processor 1010 via the components described above. In at least one embodiment, accelerometer 1041, ambient light sensor (“ALS”) 1042, compass 1043, and gyroscope 1044 may be communicatively coupled to sensor hub 1040. In at least one embodiment, thermal sensor 1039, fan 1037, keyboard 1036, and touchpad 1030 may be communicatively coupled to EC 1035. In at least one embodiment, speaker 1063, earphone 1064, and microphone (“mic”) 1065 may be communicatively coupled to audio unit (“audio codec and Class D amplifier”) 1062, which in turn may be communicatively coupled to DSP 1060. In at least one embodiment, audio unit 1062 may include, for example, but not limited to, audio encoder / decoder (“codec”) and Class D amplifier. In at least one embodiment, SIM card (“SIM”) 1057 may be communicatively coupled to WWAN unit 1056. In at least one embodiment, components such as WLAN unit 1050, Bluetooth unit 1052, and WWAN unit 1056 can be implemented as next-generation form factor (NGFF).

[0079] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is combined with... Figure 7A and / or Figure 7BDetails are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be... Figure 10 The system is used to infer or predict operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0080] Such components can be used to calculate camera-independent global visibility of elements of an object or scene model that will be used to generate images from the viewpoint of a virtual camera.

[0081] Figure 11 This is a block diagram of a processing system according to at least one embodiment. In at least one embodiment, system 1100 includes one or more processors 1102 and one or more graphics processors 1108, and may be a single-processor desktop system, a multi-processor workstation system, or a server system having a large number of processors 1102 or processor cores 1107. In at least one embodiment, system 1100 is a processing platform incorporated within a system-on-a-chip (SoC) integrated circuit for use in mobile, handheld, or embedded devices.

[0082] In at least one embodiment, system 1100 may include or be integrated into a server-based gaming platform, including a game console, mobile game console, handheld game console, or online game console, which are game and media consoles. In at least one embodiment, system 1100 is a mobile phone, smartphone, tablet computing device, or mobile internet device. In at least one embodiment, processing system 1100 may also include components coupled to or integrated into a wearable device, such as a smartwatch, smart glasses, augmented reality, or virtual reality device. In at least one embodiment, processing system 1100 is a television or set-top box device having one or more processors 1102 and a graphical interface generated by one or more graphics processors 1108.

[0083] In at least one embodiment, each of the one or more processors 1102 includes one or more processor cores 1107 for processing instructions that, when executed, perform operations against the system and user software. In at least one embodiment, each of the one or more processor cores 1107 is configured to process a specific instruction set 1109. In at least one embodiment, the instruction set 1109 may facilitate Complex Instruction Set Computing (CISC), Reduced Instruction Set Computing (RISC), or computation via Very Long Instruction Word (VLIW). In at least one embodiment, each processor core 1107 may process a different instruction set 1109, which may include instructions that facilitate the emulation of other instruction sets. In at least one embodiment, the processor core 1107 may also include other processing devices, such as a digital signal processor (DSP).

[0084] In at least one embodiment, processor 1102 includes cache memory 1104. In at least one embodiment, processor 1102 may have a single internal cache or multiple levels of internal caches. In at least one embodiment, the cache memory is shared among various components of processor 1102. In at least one embodiment, processor 1102 also uses an external cache (e.g., a Level 3 (L3) cache or a last-level cache (LLC)) (not shown), which can be shared among processor cores 1107 using known cache coherence techniques. In at least one embodiment, processor 1102 further includes a register file 1106, which may include different types of registers (e.g., integer registers, floating-point registers, status registers, and instruction pointer registers) for storing different types of data. In at least one embodiment, register file 1106 may include general-purpose registers or other registers.

[0085] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 to transmit communication signals, such as address, data, or control signals, between the processors 1102 and other components in the system 1100. In at least one embodiment, the interface bus 1110 may be a processor bus, such as a version of the Direct Media Interface (DMI) bus. In at least one embodiment, the interface bus 1110 is not limited to the DMI bus and may include one or more peripheral component interconnect buses (e.g., PCI, PCI Express), memory buses, or other types of interface buses. In at least one embodiment, the processor 1102 includes an integrated memory controller 1116 and a platform controller hub 1130. In at least one embodiment, the memory controller 1116 facilitates communication between memory devices and other components of the processing system 1100, while the platform controller hub (PCH) 1130 provides connectivity to I / O devices via a local I / O bus.

[0086] In at least one embodiment, memory device 1120 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase-change memory device, or a device with suitable performance for use as processor memory. In at least one embodiment, memory device 1120 may be used as system memory of processing system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute an application or process. In at least one embodiment, memory controller 1116 is also coupled to an optional external graphics processor 1112, which may communicate with one or more graphics processors 1108 of processor 1102 to perform graphics and media operations. In at least one embodiment, display device 1111 may be connected to processor 1102. In at least one embodiment, display device 1111 may include one or more internal display devices, such as in mobile electronic devices or laptop devices, or external display devices connected via a display interface (e.g., DisplayPort). In at least one embodiment, the display device 1111 may include a head-mounted display (HMD), such as a stereoscopic display device for virtual reality (VR) or augmented reality (AR) applications.

[0087] In at least one embodiment, the platform controller hub 1130 enables peripheral devices to connect to the storage device 1120 and the processor 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripheral devices include, but are not limited to, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, a touch sensor 1125, and a data storage device 1124 (e.g., a hard disk drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 may be connected via a storage interface (e.g., SATA) or via a peripheral bus, such as a peripheral component interconnect bus (e.g., PCI, PCIe). In at least one embodiment, the touch sensor 1125 may include a touchscreen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 may be a Wi-Fi transceiver, a Bluetooth transceiver, or a mobile network transceiver, such as a 3G, 4G, or LTE transceiver. In at least one embodiment, the firmware interface 1128 enables communication with the system firmware and may be, for example, a Unified Extensible Firmware Interface (UEFI). In at least one embodiment, network controller 1134 may enable network connectivity to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to interface bus 1110. In at least one embodiment, audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, processing system 1100 includes an optional legacy I / O controller 1140 for coupling legacy (e.g., Personal System 2 (PS / 2)) devices to system 1100. In at least one embodiment, platform controller hub 1130 may also be connected to one or more Universal Serial Bus (USB) controllers 1142 that connect input devices, such as a keyboard and mouse combination 1143, a camera 1144, or other USB input devices.

[0088] In at least one embodiment, instances of the memory controller 1116 and platform controller hub 1130 may be integrated into a discrete external graphics processor, such as external graphics processor 1112. In at least one embodiment, the platform controller hub 1130 and / or the memory controller 1116 may be external to one or more processors 1102. For example, in at least one embodiment, system 1100 may include external memory controller 1116 and platform controller hub 1130, which may be configured as a memory controller hub and peripheral controller hub in a system chipset communicating with processor 1102.

[0089] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is combined with... Figure 7A and / or Figure 7BDetails regarding the inference and / or training logic 715 are provided. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the graphics processor 1100. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs embodied in the graphics processor. Furthermore, in at least one embodiment, the inference and / or training operations described herein may use, in addition to Figure 7A and / or Figure 7B The logic is performed using logic other than that shown. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALU of the graphics processor to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0090] Such components can be used to calculate camera-independent global visibility of elements of an object or scene model that will be used to generate images from the viewpoint of a virtual camera.

[0091] Figure 12 This is a block diagram of a processor 1200 having one or more processor cores 1202A-1202N, an integrated memory controller 1214, and an integrated graphics processor 1208 according to at least one embodiment. In at least one embodiment, the processor 1200 may include additional cores, up to and including additional cores 1202N indicated by dashed boxes. In at least one embodiment, each processor core 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core may also access one or more shared cache units 1206.

[0092] In at least one embodiment, internal cache units 1204A-1204N and shared cache unit 1206 represent a cache memory hierarchy within processor 1200. In at least one embodiment, cache units 1204A-1204N may include at least one level of instruction and data cache within each processor core and one or more levels of cache in a shared intermediate cache, such as Level 2 (L2), Level 3 (L3), Level 4 (L4), or other levels of cache, wherein the highest level of cache preceding external memory is classified as LLC. In at least one embodiment, cache coherence logic maintains coherence between the various cache units 1206 and 1204A-1204N.

[0093] In at least one embodiment, the processor 1200 may further include a set of one or more bus controller units 1216 and a system agent core 1210. In at least one embodiment, one or more bus controller units 1216 manage a set of peripheral buses, such as one or more PCI or PCIe buses. In at least one embodiment, the system agent core 1210 provides management functions for various processor components. In at least one embodiment, the system agent core 1210 includes one or more integrated memory controllers 1214 to manage access to various external memory devices (not shown).

[0094] In at least one embodiment, one or more processor cores 1202A-1202N include support for concurrent multithreading. In at least one embodiment, system agent core 1210 includes components for coordinating processor cores 1202A-1202N during multithreaded processing. In at least one embodiment, system agent core 1210 may additionally include a power control unit (PCU) including logic and components for regulating one or more power states of processor cores 1202A-1202N and graphics processor 1208.

[0095] In at least one embodiment, processor 1200 further includes a graphics processor 1208 for performing graph processing operations. In at least one embodiment, graphics processor 1208 is coupled to a shared cache unit 1206 and a system proxy core 1210 including one or more integrated memory controllers 1214. In at least one embodiment, system proxy core 1210 further includes a display controller 1211 for driving graphics processor outputs to one or more coupled displays. In at least one embodiment, display controller 1211 may also be a separate module coupled to graphics processor 1208 via at least one interconnect, or it may be integrated within graphics processor 1208.

[0096] In at least one embodiment, the ring-based interconnect unit 1212 is used to couple internal components of the processor 1200. In at least one embodiment, alternative interconnect units, such as point-to-point interconnects, switched interconnects, or other technologies, may be used. In at least one embodiment, the graphics processor 1208 is coupled to the ring-based interconnect unit 1212 via I / O link 1213.

[0097] In at least one embodiment, I / O link 1213 represents at least one of a variety of I / O interconnects, including packaged I / O interconnects that facilitate communication between various processor components and high-performance embedded memory module 1218 (e.g., eDRAM module). In at least one embodiment, each of processor cores 1202A-1202N and graphics processor 1208 uses embedded memory module 1218 as a shared last-level cache.

[0098] In at least one embodiment, processor cores 1202A-1202N are homogeneous cores executing a common instruction set architecture. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of instruction set architecture (ISA), with one or more processor cores 1202A-1202N executing a common instruction set, while one or more other processor cores 1202A-1202N execute a subset of the common instruction set or a different instruction set. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of microarchitecture, with one or more cores having relatively high power consumption coupled to one or more power cores having lower power consumption. In at least one embodiment, processor 1200 may be implemented on one or more chips or implemented as a SoC integrated circuit.

[0099] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is combined with... Figure 7A and / or Figure 7B Details regarding the inference and / or training logic 715 are provided. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the processor 1200. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs embodied in... Figure 12 The graphics processor 1208, graphics core 1202A-1202N, or other components are used. Furthermore, in at least one embodiment, the inference and / or training operations described herein can use, except... Figure 7A and / or Figure 7B The logic is performed using logic other than that shown. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALU of the graphics processor 1200 to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0100] Such components can be used to calculate camera-independent global visibility of elements of an object or scene model that will be used to generate images from the viewpoint of a virtual camera.

[0101] Virtualization computing platform Figure 13 This is an example data flow diagram of process 1300 for generating and deploying an image processing and inference pipeline according to at least one embodiment. In at least one embodiment, process 1300 may be deployed for use with imaging devices, processing devices, and / or other device types at one or more facilities 1302. Process 1300 may be executed within training system 1304 and / or deployment system 1306. In at least one embodiment, training system 1304 may be used to train, deploy, and implement machine learning models (e.g., neural networks, object detection algorithms, computer vision algorithms, etc.) for use in deployment system 1306. In at least one embodiment, deployment system 1306 may be configured to offload processing and computing resources in a distributed computing environment to reduce the infrastructure requirements of facility 1302. In at least one embodiment, one or more applications in the pipeline may use or invoke services of deployment system 1306 (e.g., inference, visualization, computation, AI, etc.) during application execution.

[0102] In at least one embodiment, some applications used in the advanced processing and inference pipeline may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, a machine learning model may be trained at facility 1302 using data 1308 (e.g., imaging data) generated at facility 1302 (and stored on one or more Picture Archiving and Communication System (PACS) servers at facility 1302), imaging or sequencing data 1308 from another or more facilities, or a combination thereof. In at least one embodiment, training system 1304 may be used to provide applications, services, and / or other resources to generate a deployable machine learning model for the work of deploying system 1306.

[0103] In at least one embodiment, the model registry 1324 may be supported by an object storage system that supports version control and object metadata. In at least one embodiment, the object storage may be accessed from within a cloud platform via, for example, a cloud storage-compatible application programming interface (API). In at least one embodiment, machine learning models within the model registry 1324 may be uploaded, listed, modified, or deleted by the developer or partner of a system interacting with the API. In at least one embodiment, the API may provide access to methods that allow users with appropriate credentials to associate models with applications, enabling the models to be executed as part of the containerized instantiation of the application.

[0104] In at least one embodiment, training system 1304 ( Figure 13This can include situations where facility 1302 is training its own machine learning model or has an existing machine learning model that needs optimization or updating. In at least one embodiment, imaging data 1308 generated by imaging equipment, sequencing equipment, and / or other types of equipment can be received. In at least one embodiment, once imaging data 1308 is received, AI-assisted annotation 1310 can be used to help generate annotations corresponding to imaging data 1308 for use as ground-based data for machine learning models. In at least one embodiment, AI-assisted annotation 1310 can include one or more machine learning models (e.g., convolutional neural networks (CNNs)) that can be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain equipment). In at least one embodiment, AI-assisted annotation 1310 can then be used directly or adjusted or fine-tuned using annotation tools to generate ground-based data. In at least one embodiment, AI-assisted annotation 1310, labeled data 1312, or a combination thereof can be used as ground-based data for training machine learning models. In at least one embodiment, the trained machine learning model may be referred to as output model 1316 and may be used by deployment system 1306 as described herein.

[0105] In at least one embodiment, the training pipeline may include a scenario where facility 1302 requires a machine learning model to perform one or more processing tasks for deploying one or more applications in system 1306, but facility 1302 may not currently have such a machine learning model (or may not have a model optimized, efficient, or effective for this purpose). In at least one embodiment, an existing machine learning model may be selected from model registry 1324. In at least one embodiment, model registry 1324 may include machine learning models trained to perform various inference tasks on imaging data. In at least one embodiment, the machine learning model in model registry 1324 may be trained on imaging data from a different facility (e.g., a remote facility) instead of facility 1302. In at least one embodiment, the machine learning model may have already been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when training on imaging data from a specific location, training may be performed at that location, or at least in a manner that protects the confidentiality of the imaging data or restricts the transfer of the imaging data from off-site locations. In at least one embodiment, once a model has been trained or partially trained at one location, a machine learning model can be added to model registry 1324. In at least one embodiment, the machine learning model can then be retrained or updated at any number of other facilities, and the retrained or updated model can be used in model registry 1324. In at least one embodiment, a machine learning model (referred to as output model 1316) can then be selected from model registry 1324, and can be executed in deployment system 1306 for one or more processing tasks of one or more applications for deploying the system.

[0106] In at least one embodiment, the scenario may include facility 1302, which requires a machine learning model to perform one or more processing tasks for deploying one or more applications in system 1306, but facility 1302 may not currently have such a machine learning model (or may not have an optimized, efficient, or effective model). In at least one embodiment, the machine learning model selected from model registry 1324 may not be fine-tuned or optimized for the imaging data 1308 generated at facility 1302 due to population variability, robustness, anomalous diversity of training data, and / or other problems with the training data used to train the machine learning model. In at least one embodiment, AI-assisted annotation 1310 may be used to help generate annotations corresponding to the imaging data 1308 for use as ground-based data for training or updating the machine learning model. In at least one embodiment, labeled data 1312 may be used as ground-based data for training the machine learning model. In at least one embodiment, retraining or updating the machine learning model may be referred to as model training 1314. In at least one embodiment, model training 1314 (e.g., AI-assisted annotation 1310, labeled clinical data 1312, or a combination thereof) can be used as ground-based data to retrain or update the machine learning model. In at least one embodiment, the trained machine learning model can be referred to as output model 1316 and can be used by deployment system 1306, as described herein.

[0107] In at least one embodiment, deployment system 1306 may include software 1318, service 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, deployment system 1306 may include a software "stack" such that software 1318 can be built on top of service 1320 and can be used to perform some or all of the processing tasks, and service 1320 and software 1318 can be built on top of hardware 1322 and can be used to perform the deployment system's processing, storage, and / or other computational tasks. In at least one embodiment, software 1318 may include any number of different containers, each of which can perform an instantiation of an application. In at least one embodiment, each application can perform one or more processing tasks (e.g., inference, object detection, feature detection, segmentation, image enhancement, calibration, etc.) in a high-level processing and inference pipeline. In at least one embodiment, in addition to receiving and configuring imaging data for use by each container and / or by facility 1302 after processing through the pipeline, advanced processing and inference pipelines (e.g., to convert output back to available data types) can be defined based on the selection of different containers desired or required for processing imaging data 1308. In at least one embodiment, a combination of containers within software 1318 (e.g., constituting a pipeline) may be referred to as a virtual instrument (as described in more detail herein), and the virtual instrument may utilize service 1320 and hardware 1322 to perform some or all of the processing tasks of an application instantiated within the container.

[0108] In at least one embodiment, the data processing pipeline may receive input data (e.g., imaging data 1308) in a specific format in response to an inference request (e.g., a request from a user of deployment system 1306). In at least one embodiment, the input data may represent one or more images, videos, and / or other data representations generated by one or more imaging devices. In at least one embodiment, the data may be preprocessed as part of the data processing pipeline to prepare it for processing by one or more applications. In at least one embodiment, post-processing may be performed on the output of one or more inference tasks or other processing tasks of the pipeline to prepare output data for the next application and / or to prepare output data for user transmission and / or use (e.g., as a response to an inference request). In at least one embodiment, the inference task may be performed by one or more machine learning models, such as trained or deployed neural networks, which may include the output model 1316 of training system 1304.

[0109] In at least one embodiment, the tasks of the data processing pipeline can be encapsulated in containers, each container representing a discrete, fully functional instantiation of an application and a virtualized computing environment capable of referencing a machine learning model. In at least one embodiment, containers or applications can be published to a private (e.g., limited access) area of ​​a container registry (described in more detail herein), and trained or deployed models can be stored in a model registry 1324 and associated with one or more applications. In at least one embodiment, an image of the application (e.g., a container image) can be used in the container registry, and once a user selects an image from the container registry for deployment in the pipeline, that image can be used to generate containers for instantiation of the application for use by the user's system.

[0110] In at least one embodiment, a developer (e.g., a software developer, clinician, physician, etc.) can develop, publish, and store an application (e.g., as a container) for performing image processing and / or inference on provided data. In at least one embodiment, a software development kit (SDK) associated with the system can be used to perform development, publication, and / or storage (e.g., to ensure the developed application and / or container conforms to or is compatible with the system). In at least one embodiment, the developed application can be tested locally using the SDK (e.g., at a first facility, testing data from a first facility), the SDK serving as a system (e.g., Figure 12 System 1200 may support at least some services 1320. In at least one embodiment, since DICOM objects may contain one to hundreds of images or other data types, and due to variations in the data, the developer may be responsible for managing (e.g., setting up constructs for preprocessing built into the application, etc.) the extraction and preparation of incoming data. In at least one embodiment, once verified by system 1300 (e.g., for accuracy), the application becomes available in the container registry for user selection and / or implementation to perform one or more processing tasks on data at the user's facility (e.g., a second facility).

[0111] In at least one embodiment, the developer can then share the application or container over a network for the system (e.g., Figure 13The system 1300 allows for user access and use. In at least one embodiment, completed and validated applications or containers may be stored in a container registry, and associated machine learning models may be stored in a model registry 1324. In at least one embodiment, a requesting entity (which provides an inference or image processing request) may browse the container registry and / or model registry 1324 to obtain applications, containers, datasets, machine learning models, etc., select desired combinations of elements to include in the data processing pipeline, and submit an image processing request. In at least one embodiment, the request may include input data necessary to execute the request (and, in some examples, patient-related data), and / or may include selections of applications and / or machine learning models to be executed when the request is processed. In at least one embodiment, the request may then be passed to one or more components of the deployment system 1306 (e.g., the cloud) to perform processing in the data processing pipeline. In at least one embodiment, processing performed by the deployment system 1306 may include referencing elements (e.g., applications, containers, models, etc.) selected from the container registry and / or model registry 1324. In at least one embodiment, once the results are generated through the pipeline, the results can be returned to the user for reference (e.g., for viewing in a suite of viewing applications executed locally, on a local workstation, or on a terminal).

[0112] In at least one embodiment, service 1320 may be utilized to assist in processing or executing applications or containers in the pipeline. In at least one embodiment, service 1320 may include computing services, artificial intelligence (AI) services, visualization services, and / or other service types. In at least one embodiment, service 1320 may provide functionality common to one or more applications in software 1318, thus abstracting functionality into services that can be invoked or utilized by applications. In at least one embodiment, the functionality provided by service 1320 can operate dynamically and more efficiently, while also allowing applications to process data in parallel (e.g., using...). Figure 12The parallel computing platform 1230 in the system can be scaled well. In at least one embodiment, it is not required that each application providing the same functionality as the shared service 1320 must have a corresponding instance of the service 1320, but the service 1320 can be shared between and among various applications. In at least one embodiment, as a non-limiting example, the service may include an inference server or engine that can be used to perform detection or segmentation tasks. In at least one embodiment, a model training service may be included, which can provide the ability to train and / or retrain machine learning models. In at least one embodiment, a data augmentation service may be further included, which can provide GPU-accelerated data (e.g., DICOM, RIS, CIS, conforming to REST, RPC, raw, etc.) extraction, resizing, scaling, and / or other enhancements. In at least one embodiment, a visualization service may be used, which can add image rendering effects (e.g., ray tracing, rasterization, denoising, sharpening, etc.) to add realism to two-dimensional (2D) and / or three-dimensional (3D) models. In at least one embodiment, a virtual instrument service may be included, which provides beamforming, segmentation, inference, imaging, and / or support for other applications within the virtual instrument pipeline.

[0113] In at least one embodiment, where service 1320 includes an AI service (e.g., an inference service), as part of application execution, one or more machine learning models can be executed by invoking (e.g., as an API call) the inference service (e.g., an inference server) to execute one or more machine learning models or their processing. In at least one embodiment, where another application includes one or more machine learning models for a segmentation task, the application can invoke the inference service to execute the machine learning models for performing one or more processing operations associated with the segmentation task. In at least one embodiment, software 1318 implementing advanced processing and inference pipelines, including a segmentation application and an anomaly detection application, can be pipelined because each application can invoke the same inference service to execute one or more inference tasks.

[0114] In at least one embodiment, hardware 1322 may include a GPU, CPU, graphics card, AI / deep learning system (e.g., an AI supercomputer, such as NVIDIA's DGX), cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient, specially built support for software 1318 and services 1320 in deployment system 1306. In at least one embodiment, GPU processing may be used to perform local processing (e.g., at facility 1302) within the AI / deep learning system, in the cloud system, and / or other processing components of deployment system 1306 to improve the efficiency, accuracy, and performance of image processing and generation. In at least one embodiment, as a non-limiting example, software 1318 and / or services 1320 may be optimized for GPU processing in relation to deep learning, machine learning, and / or high-performance computing. In at least one embodiment, at least some of the computing environment of deployment system 1306 and / or training system 1304 may be executed in a data center, one or more supercomputers, or high-performance computing systems with GPU-optimized software (e.g., a hardware and software combination of an NVIDIA DGX system). In at least one embodiment, as described herein, hardware 1322 may include any number of GPUs that can be invoked to perform data processing in parallel. In at least one embodiment, the cloud platform may also include GPU-optimized execution for deep learning tasks, GPU processing for machine learning tasks, or other computational tasks. In at least one embodiment, an AI / deep learning supercomputer and / or GPU-optimized software (e.g., as provided on NVIDIA's DGX systems) may be used as a hardware abstraction and scaling platform to execute the cloud platform (e.g., NVIDIA's NGC). In at least one embodiment, the cloud platform may integrate application container cluster systems or coordination systems (e.g., Kubernetes) across multiple GPUs to achieve seamless scaling and load balancing.

[0115] Figure 14 This is a system diagram of an example system 1400 for generating and deploying an imaging deployment pipeline according to at least one embodiment. In at least one embodiment, system 1400 can be used to implement Figure 13 The process 1300 and / or other processes include advanced processing and inference pipelines. In at least one embodiment, system 1400 may include training system 1304 and deployment system 1306. In at least one embodiment, training system 1304 and deployment system 1306 may be implemented using software 1318, service 1320 and / or hardware 1322, as described herein.

[0116] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) may be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 may be implemented locally (in relation to a healthcare facility) or as a combination of cloud computing resources and local computing resources. In at least one embodiment, access to the API in cloud 1426 may be restricted to authorized users by establishing security measures or protocols. In at least one embodiment, the security protocol may include a network token, which may be signed by an authentication service (e.g., AuthN, AuthZ, Gluecon, etc.) and may carry appropriate authorization. In at least one embodiment, the API of the virtual instrument (described herein) or other instances of system 1400 may be restricted to a set of public IPs that have been audited or authorized for interaction.

[0117] In at least one embodiment, the various components of system 1400 may communicate with each other using any of a variety of different network types, including but not limited to local area networks (LANs) and / or wide area networks (WANs) via wired and / or wireless communication protocols. In at least one embodiment, communication between facilities and components of system 1400 (e.g., for sending inference requests, for receiving the results of inference requests, etc.) may be transmitted via one or more data buses, wireless data protocols (Wi-Fi), wired data protocols (e.g., Ethernet), etc.

[0118] In at least one embodiment, similar to the description herein. Figure 13 As described, training system 1304 can execute training pipeline 1404. In at least one embodiment, where deployment system 1306 uses one or more machine learning models in deployment pipeline 1410, training pipeline 1404 can be used to train or retrain one or more (e.g., pre-trained) models, and / or implement one or more pre-trained models 1406 (e.g., without retraining or updating). In at least one embodiment, as a result of training pipeline 1404, output model 1316 can be generated. In at least one embodiment, training pipeline 1404 can include any number of processing steps, such as, but not limited to, transformation or adaptation of imaging data (or other input data). In at least one embodiment, different training pipelines 1404 can be used for different machine learning models used by deployment system 1306. In at least one embodiment, similar to the description of... Figure 13 The training pipeline 1404 described in the first example can be used for the first machine learning model, similar to the one described above. Figure 13 The training pipeline 1404 described in the second example can be used for a second machine learning model, similar to the one described above. Figure 13The training pipeline 1404 of the third example described can be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 can be used according to the requirements of each corresponding machine learning model. In at least one embodiment, one or more machine learning models may have already been trained and are ready for deployment, so the training system 1304 may not perform any processing on the machine learning models, and one or more machine learning models may be implemented by the deployment system 1306.

[0119] In at least one embodiment, depending on the implementation or embodiment, the output model 1316 and / or the pre-trained model 1406 may include any type of machine learning model. In at least one embodiment, and not limited thereto, the machine learning model used by system 1400 may include models using linear regression, logistic regression, decision trees, support vector machines (SVM), Naive Bayes, k-nearest neighbors (Knn), k-means clustering, random forests, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., autoencoders, convolutions, recursion, perceptrons, long / short-term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid state machines, etc.), and / or other types of machine learning models.

[0120] In at least one embodiment, the training pipeline 1404 may include AI-assisted annotations, as described herein regarding at least Figure 14B. More detailed description. In at least one embodiment, labeled clinical data 1312 can be generated using any number of techniques (e.g., conventional annotation). In at least one embodiment, in some examples, labels or other annotations can be generated by drawing programs (e.g., annotation programs), computer-aided design (CAD) programs, tagging programs, another type of application suitable for generating annotations or labels for ground reality, and / or can be hand-drawn. In at least one embodiment, ground reality data can be synthetically generated (e.g., generated from computer models or renderings), realistically generated (e.g., designed and generated from real-world data), automatically generated by machines (e.g., extracting features from data using feature analysis and learning, and then generating labels), manually annotated (e.g., taggers or annotation experts, defining the placement of labels), and / or combinations thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data types used by machine learning models), there may be corresponding ground reality data generated by training system 1304. In at least one embodiment, AI-assisted annotation can be performed as part of deployment pipeline 1410; supplementing or replacing AI-assisted annotation included in training pipeline 1404. In at least one embodiment, system 1400 may include a multi-layer platform, which may include a software layer (e.g., software 1318) of a diagnostic application (or other application type) capable of performing one or more medical imaging and diagnostic functions. In at least one embodiment, system 1400 may be communicatively coupled (e.g., via an encrypted link) to a network of PACS servers in one or more facilities. In at least one embodiment, system 1400 may be configured to access and reference data from PACS servers to perform operations such as training machine learning models, deploying machine learning models, image processing, inference, and / or other operations.

[0121] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or certified API that can invoke (e.g., call) an application or container from an external environment (e.g., facility 1302). In at least one embodiment, the application may then invoke or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with their respective applications, and the software 1318 and / or services 1320 may utilize hardware 1322 to perform processing tasks efficiently and effectively. In at least one embodiment, communication sent to or received by training system 1304 and deployment system 1306 may occur using a pair of DICOM adapters 1402A, 1402B.

[0122] In at least one embodiment, deployment system 1306 may execute deployment pipeline 1410. In at least one embodiment, deployment pipeline 1410 may include any number of applications, which may be sequential, non-sequential, or otherwise applied to imaging data (and / or other data types) – including AI-assisted annotation, the imaging data being generated by imaging devices, sequencing devices, genomics devices, etc., as described above. In at least one embodiment, as described herein, deployment pipeline 1410 for an individual device may be referred to as a virtual instrument for the device (e.g., a virtual ultrasound instrument, a virtual CT scanner, a virtual sequencing instrument, etc.). In at least one embodiment, for a single device, more than one deployment pipeline 1410 may exist, depending on the desired information from the data generated from the device. In at least one embodiment, a first deployment pipeline 1410 may exist if it is desired to detect an anomaly from an MRI machine, and a second deployment pipeline 1410 may exist if it is desired to perform image enhancement from the output of the MRI machine.

[0123] In at least one embodiment, the image generation application may include processing tasks that utilize machine learning models. In at least one embodiment, a user may wish to use their own machine learning model or select a machine learning model from the model registry 1324. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model to be included in the application performing the processing tasks. In at least one embodiment, the application may be optional and customizable, and by defining the application's construction, the deployment and implementation of the application for a specific user is presented as a more seamless user experience. In at least one embodiment, by leveraging other features of system 1400 (e.g., service 1320 and hardware 1322), the deployment pipeline 1410 can be more user-friendly, provide easier integration, and produce more accurate, efficient, and timely results.

[0124] In at least one embodiment, deployment system 1306 may include a user interface (UI) 1414 (e.g., a graphical user interface, a web interface, etc.) that can be used to select applications to be included in deployment pipeline 1410, deploy applications, modify or change applications or their parameters or configurations, use and interact with deployment pipeline 1410 during setup and / or deployment, and / or otherwise interact with deployment system 1306. In at least one embodiment, although not shown with respect to training system 1304, UI 1414 (or different user interfaces) can be used to select models to be used in deployment system 1306, to select models to be trained or retrained in training system 1304, and / or to otherwise interact with training system 1304.

[0125] In at least one embodiment, in addition to the application coordination system 1428, a pipeline manager 1412 may be used to manage interactions between applications or containers deployed through the pipeline 1410 and services 1320 and / or hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate interactions from application to application, from application to service 1320, and / or from application or service to hardware 1322. In at least one embodiment, although shown as included in software 1318, this is not intended to be limiting, and in some examples, the pipeline manager 1412 may be included in service 1320. In at least one embodiment, the application coordination system 1428 (e.g., Kubernetes, DOCKER, etc.) may include a container coordination system that can group applications into containers as logical units for coordination, management, scaling, and deployment. In at least one embodiment, by associating applications from the deployment pipeline 1410 (e.g., rebuilding applications, splitting applications, etc.) with individual containers, each application can execute in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0126] In at least one embodiment, each application and / or container (or its image) can be developed, modified, and deployed independently (e.g., a first user or developer can develop, modify, and deploy a first application, and a second user or developer can develop, modify, and deploy a second application separate from the first user or developer). This allows focus on the tasks of a single application and / or container without being hindered by the tasks of another application or container. In at least one embodiment, the pipeline manager 1412 and the application coordination system 1428 can facilitate communication and collaboration between different containers or applications. In at least one embodiment, the application coordination system 1428 and / or the pipeline manager 1412 can facilitate communication and resource sharing between and within each application or container, provided that the expected inputs and / or outputs of each container or application are known to the system (e.g., based on the application or container's architecture). In at least one embodiment, since one or more applications or containers in the deployment pipeline 1410 can share the same services and resources, the application coordination system 1428 can coordinate, load balance, and determine the sharing of services or resources between and within the various applications or containers. In at least one embodiment, the scheduler can be used to track the resource requirements of applications or containers, the current or planned use of these resources, and resource availability. Therefore, in at least one embodiment, the scheduler can allocate resources to different applications and distribute resources between and among applications, taking into account the system's needs and availability. In some examples, the scheduler (and / or other components of the application coordination system 1428) can determine resource availability and distribution based on constraints imposed on the system (e.g., user constraints), such as Quality of Service (QoS), the urgency of data output (e.g., to determine whether to perform real-time processing or delayed processing), etc.

[0127] In at least one embodiment, service 1320, utilized and shared by applications or containers in deployment system 1306, may include computing service 1416, AI service 1418, visualization service 1420, and / or other service types. In at least one embodiment, an application may invoke (e.g., execute) one or more services 1320 to perform processing operations for the application. In at least one embodiment, an application may utilize computing service 1416 to perform supercomputing or other high-performance computing (HPC) tasks. In at least one embodiment, one or more computing services 1416 may be utilized to perform parallel processing (e.g., using parallel computing platform 1430) to process data substantially simultaneously through one or more applications and / or one or more tasks of a single application. In at least one embodiment, parallel computing platform 1430 (e.g., NVIDIA's CUDA) may implement general-purpose computing on a GPU (GPGPU) (e.g., GPU / graphics 1422). In at least one embodiment, the software layer of parallel computing platform 1430 may provide access to the GPU's virtual instruction set and parallel computing elements to execute computing kernels. In at least one embodiment, the parallel computing platform 1430 may include memory, and in some embodiments, memory may be shared between and within multiple containers, and / or between and within different processing tasks within a single container. In at least one embodiment, inter-process communication (IPC) calls may be generated for multiple containers and / or multiple processes within containers to enable the use of the same data (e.g., multiple different stages of one or more applications processing the same information) from a shared memory segment of the parallel computing platform 1430. In at least one embodiment, instead of copying data and moving it to different locations in memory (e.g., read / write operations), the same data in the same memory location can be used for any number of processing tasks (e.g., at the same time, at different times, etc.). In at least one embodiment, this information about the new location of the data can be stored and shared between applications because the resulting data from processing is used to generate new data. In at least one embodiment, the location of the data, and the location of the updated or modified data, may be part of the definition of how the payload in the container is understood.

[0128] In at least one embodiment, AI service 1418 may be used to perform an inference service for executing a machine learning model associated with the application (e.g., a task to perform one or more processing tasks of the application). In at least one embodiment, AI service 1418 may utilize AI system 1424 to execute a machine learning model (e.g., a neural network such as a CNN) for segmentation, reconstruction, object detection, feature detection, classification, and / or other inference tasks. In at least one embodiment, the application deploying pipeline 1410 may use one or more output models 1316 of self-training system 1304 and / or other models of the application to perform inference on imaging data. In at least one embodiment, two or more examples of using application coordination system 1428 (e.g., a scheduler) for inference may be available. In at least one embodiment, a first category may include a high-priority / low-latency path that can implement a higher service level protocol, such as for performing inference on urgent requests in emergency situations or for radiologists during diagnostic procedures. In at least one embodiment, a second category may include a standard priority path that can be used for requests that may not be urgent or for situations where analysis can be performed at a later time. In at least one embodiment, the application coordination system 1428 may allocate resources (e.g., services 1320 and / or hardware 1322) based on priority paths for different inference tasks of the AI ​​service 1418.

[0129] In at least one embodiment, shared memory may be installed into AI service 1418 in system 1400. In at least one embodiment, shared memory may operate as a cache (or other storage device type) and may be used to process inference requests from applications. In at least one embodiment, when an inference request is submitted, a set of API instances of deployment system 1306 may receive the request and may select one or more instances (e.g., for best fit, for load balancing, etc.) to process the request. In at least one embodiment, to process the request, the request may be fed into a database, and if not already in the cache, a machine learning model may be located from model registry 1324. A verification step may ensure that an appropriate machine learning model is loaded into the cache (e.g., shared memory), and / or a copy of the model may be saved to the cache. In at least one embodiment, if the application is not already running or there are not enough instances of the application, a scheduler (e.g., the scheduler of pipeline manager 1412) may be used to start the application referenced in the request. In at least one embodiment, if an inference server has not yet been started to execute the model, an inference server may be started. Any number of inference servers may be started for each model. In at least one embodiment, in a pull model that clusters inference servers, the model can be cached whenever load balancing is favorable. In at least one embodiment, the inference servers can be statically loaded into the corresponding distributed servers.

[0130] In at least one embodiment, an inference server running in a container can be used to perform inference. In at least one embodiment, an instance of the inference server can be associated with a model (and optionally multiple versions of the model). In at least one embodiment, if an instance of the inference server does not exist when a request to perform inference on the model is received, a new instance can be loaded. In at least one embodiment, when the inference server is started, a model can be passed to the inference server, allowing the same container to be used to serve different models, as long as the inference server runs as different instances.

[0131] In at least one embodiment, during application execution, an inference request for a given application can be received, and a container (e.g., an instance of a hosted inference server) can be loaded (if not already loaded), and a launcher can be invoked. In at least one embodiment, preprocessing logic within the container can (e.g., using a CPU and / or GPU) load, decode, and / or perform any additional preprocessing on the incoming data. In at least one embodiment, once the data is ready for inference, the container can infer the data as needed. In at least one embodiment, this can include a single inference call for an image (e.g., a hand X-ray) or can request inference for hundreds of images (e.g., a chest CT scan). In at least one embodiment, the application can summarize the results before completion, which may include, but is not limited to, a single confidence score, pixel-level segmentation, voxel-level segmentation, generating visualizations, or generating text to summarize the results. In at least one embodiment, different priorities can be assigned to different models or applications. For example, some models may have a real-time (TAT less than 1 minute) priority, while other models may have a lower priority (e.g., TAT less than 10 minutes). In at least one embodiment, model execution time can be measured from the requesting agency or entity, and may include cooperative network traversal time and inference service execution time.

[0132] In at least one embodiment, the transfer of requests between service 1320 and the inference application can be hidden behind a software development kit (SDK) and robust transfer can be provided via queues. In at least one embodiment, requests are placed in queues via an API for individual application / tenant ID combinations, and the SDK pulls requests from the queues and provides them to the application. In at least one embodiment, the name of the queue can be provided in the environment where the SDK picks up the queue. In at least one embodiment, asynchronous communication via queues may be useful because it allows any instance of the application to pick up work when it becomes available. Results can be sent back via queues to ensure no data loss. In at least one embodiment, queues can also provide the ability to partition work, as the highest priority work can go into a queue connected to a majority of instances of the application, while the lowest priority work can go into a queue connected to a single instance that processes tasks in the order they are received. In at least one embodiment, the application can run on a GPU-accelerated instance generated in cloud 1426, and the inference service can perform inference on the GPU.

[0133] In at least one embodiment, visualization service 1420 can be used to generate visualizations for viewing the output of application and / or deployment pipeline 1410. In at least one embodiment, visualization service 1420 can utilize GPU / graphics 1422 to generate visualizations. In at least one embodiment, visualization service 1420 can implement rendering effects such as ray tracing to generate higher quality visualizations. In at least one embodiment, visualizations can include, but are not limited to, 2D image rendering, 3D volume rendering, 3D volume reconstruction, 2D tomographic slicing, virtual reality display, augmented reality display, etc. In at least one embodiment, a virtualized environment can be used to generate virtual interactive displays or environments (e.g., virtual environments) for system users (e.g., doctors, nurses, radiologists, etc.) to interact with. In at least one embodiment, visualization service 1420 can include an internal visualizer, cinematic and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0134] In at least one embodiment, hardware 1322 may include GPU / graphics 1422, AI system 1424, cloud 1426, and / or any other hardware for performing training system 1304 and / or deployment system 1306. In at least one embodiment, GPU / graphics 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs that can be used to perform processing tasks for any feature or function of computing service 1416, AI service 1418, visualization service 1420, other services, and / or software 1318. For example, for AI service 1418, GPU / graphics 1422 may be used to perform preprocessing on imaging data (or other data types used by machine learning models), postprocessing on the output of machine learning models, and / or inference (e.g., to execute machine learning models). In at least one embodiment, cloud 1426, AI system 1424, and / or other components of system 1400 may use GPU / graphics 1422. In at least one embodiment, cloud 1426 may include a GPU-optimized platform for deep learning tasks. In at least one embodiment, AI system 1424 may use a GPU, and one or more AI systems 1424 may be used to perform cloud 1426 (or at least part of a task for deep learning or inference). Similarly, although hardware 1322 is shown as a discrete component, this is not intended to be limiting, and any component of hardware 1322 may be combined with or utilized by any other component of hardware 1322.

[0135] In at least one embodiment, AI system 1424 may include a specially built computing system (e.g., a supercomputer or HPC) configured for inference, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, in addition to CPU, RAM, memory, and / or other components, features, or functions, AI system 1424 (e.g., NVIDIA's DGX) may also include software (e.g., a software stack) that can be used to perform GPU-optimized tasks using multiple GPUs / graphics 1422. In at least one embodiment, one or more AI systems 1424 may be implemented in a cloud 1426 (e.g., in a data center) to perform some or all of the AI-based processing tasks of system 1400.

[0136] In at least one embodiment, cloud 1426 may include GPU-accelerated infrastructure (e.g., NVIDIA's NGC) that can provide a GPU-optimized platform for performing processing tasks of system 1400. In at least one embodiment, cloud 1426 may include AI system 1424 for performing one or more AI-based tasks of system 1400 (e.g., as a hardware abstraction and scaling platform). In at least one embodiment, cloud 1426 may be integrated with application coordination system 1428 utilizing multiple GPUs to achieve seamless scaling and load balancing between and within applications and services 1320. In at least one embodiment, as described herein, cloud 1426 may be responsible for performing at least some of the services 1320 of system 1400, including computing service 1416, AI service 1418, and / or visualization service 1420. In at least one embodiment, cloud 1426 may perform large and small batch inference (e.g., perform NVIDIA's TENSORRT), provide accelerated parallel computing APIs and platform 1430 (e.g., NVIDIA's CUDA), perform application coordination system 1428 (e.g., KUBERNETES), provide graphics rendering APIs and platform (e.g., for ray tracing, 2D graphics, 3D graphics and / or other rendering techniques to produce higher quality cinematic effects), and / or provide other functionalities for system 1400.

[0137] Figure 15A A data flow diagram of a process 1500 for training, retraining, or updating a machine learning model according to at least one embodiment is shown. In at least one embodiment, a non-limiting example can be used. Figure 14 The system 1400 executes the process 1500. In at least one embodiment, the process 1500 may utilize services and / or hardware, as described herein. In at least one embodiment, the refined model 1512 generated by the process 1500 may be executed by a deployment system for one or more containerized applications in the deployment pipeline.

[0138] In at least one embodiment, model training 1514 may include retraining or updating the initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data, such as customer dataset 1506, and / or new ground reality data associated with the input data). In at least one embodiment, to retrain or update the initial model 1504, the output or loss layer of the initial model 1504 may be reset or deleted, and / or replaced with an updated or new output or loss layer. In at least one embodiment, the initial model 1504 may have previously fine-tuned parameters (e.g., weights and / or biases) retained from previous training, so training or retraining 1514 may not require as much time or processing as training the model from scratch. In at least one embodiment, during model training 1514, when generating predictions on the new customer dataset 1506 by resetting or replacing the output or loss layer of the initial model 1504, the parameters of the new dataset may be updated and readjusted based on the loss calculation associated with the accuracy of the output or loss layer.

[0139] In at least one embodiment, the pre-trained model 1506 may be stored in a data store or registry. In at least one embodiment, the pre-trained model 1506 may have been trained at least partially at one or more facilities other than the facility executing process 1500. In at least one embodiment, to protect the privacy and rights of patients, subjects, or customers at different facilities, the pre-trained model 1506 may have been trained locally using locally generated customer or patient data. In at least one embodiment, the pre-trained model 1506 may be trained using cloud and / or other hardware, but confidential, privacy-protected patient data may not be transferred to, used by, or accessed by any component of the cloud (or other non-local hardware). In at least one embodiment, if the pre-trained model 1506 is trained using patient data from more than one facility, the pre-trained model 1506 may have been trained separately for each facility before training on patient or customer data from another facility. In at least one embodiment, such as when customer or patient data has been published for privacy reasons (e.g., by abandonment, for experimental purposes, etc.), or where customer or patient data is included in a public dataset, customer or patient data from any number of facilities can be used to train a pre-trained model 1506 locally and / or externally, such as in a data center or other cloud computing infrastructure.

[0140] In at least one embodiment, when selecting an application for use in the deployment pipeline, the user may also select a machine learning model for a specific application. In at least one embodiment, the user may not have a model available, so the user may select a pre-trained model to use with the application. In at least one embodiment, the pre-trained model may not be optimized to generate accurate results on the user facility's customer dataset 1506 (e.g., based on patient diversity, demographics, type of medical imaging equipment used, etc.). In at least one embodiment, the pre-trained model may be updated, retrained, and / or fine-tuned for use at various facilities before being deployed into the deployment pipeline for use with one or more applications.

[0141] In at least one embodiment, a user may select a pre-trained model to update, retrain, and / or fine-tune, and this pre-trained model may be referred to as the initial model 1504 of the training system in process 1500. In at least one embodiment, a client dataset 1506 (e.g., imaging data, genomic data, sequencing data, or other data types generated by equipment at the facility) may be used to perform model training (which may include, but is not limited to, transfer learning) on ​​the initial model 1504 to generate a refined model 1512. In at least one embodiment, ground-based data corresponding to the client dataset 1506 may be generated by the training system 1304. In at least one embodiment, ground-based data may be generated at the facility, at least in part, by clinicians, scientists, physicians, or practitioners.

[0142] In at least one embodiment, AI-assisted annotation may be used to generate ground-based data in some examples. In at least one embodiment, AI-assisted annotation (e.g., implemented using an AI-assisted annotation SDK) may leverage machine learning models (e.g., neural networks) to generate suggested or predicted ground-based data for a customer dataset. In at least one embodiment, a user may use the annotation tool within a user interface (graphical user interface (GUI)) on a computing device.

[0143] In at least one embodiment, user 1510 can interact with the GUI via computing device 1508 to edit or fine-tune annotations or automatic annotations. In at least one embodiment, polygon editing features can be used to move the vertices of a polygon to more precise or fine-tuned positions.

[0144] In at least one embodiment, once the customer dataset 1506 has associated ground-based data, the ground-based data (e.g., from AI-assisted annotations, manual labeling, etc.) can be used to generate a refined model 1512 during model training. In at least one embodiment, the customer dataset 1506 can be applied to the initial model 1504 an arbitrary number of times, and the ground-based data can be used to update the parameters of the initial model 1504 until an acceptable level of accuracy is achieved for the refined model 1512. In at least one embodiment, once the refined model 1512 is generated, it can be deployed in one or more deployment pipelines at the facility to perform one or more processing tasks related to medical imaging data.

[0145] In at least one embodiment, the refined model 1512 can be uploaded to a pre-trained model registry for selection by another facility. In at least one embodiment, this process can be performed at any number of facilities, allowing the refined model 1512 to be further refined an arbitrary number of times on a new dataset to generate a more general model.

[0146] Figure 15B This is an example illustration of a client-server architecture 1532 for enhancing an annotation tool using a pre-trained annotation model, according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 may be instantiated based on the client-server architecture 1532. In at least one embodiment, the AI-assisted annotation tool 1536 in an imaging application can assist radiologists, for example, in identifying organs and abnormalities. In at least one embodiment, the imaging application may include software tools, as a non-limiting example, that help user 1510 identify several extreme points on a specific organ of interest in a raw image 1534 (e.g., in a 3D MRI or CT scan) and receive automatic annotation results for all 2D slices of that specific organ. In at least one embodiment, the results may be stored in a data store as training data 1538 and used as (e.g., but not limited to) ground-based data for training. In at least one embodiment, when computing device 1508 sends extreme points for AI-assisted annotation, for example, a deep learning model may receive this data as input and return inference results for segmenting organs or abnormalities. In at least one embodiment, a pre-instantiated annotation tool (e.g., Figure 15BThe AI-assisted annotation tool 1536 can be enhanced by making API calls (e.g., API call 1544) to a server (such as annotation assistant server 1540), which may include a set of pre-trained models 1542 stored, for example, in an annotation model registry. In at least one embodiment, the annotation model registry may store the pre-trained models 1542 (e.g., machine learning models, such as deep learning models) pre-trained to perform AI-assisted annotation on specific organs or anomalies. In at least one embodiment, these models can be further updated using a training pipeline. In at least one embodiment, the pre-installed annotation tool can be improved over time as new labeled data is added.

[0147] The various embodiments can be described by the following terms: 1. A computer-implemented method, comprising: Select at least one starting mesh cell of a virtual mesh aligned with the object model, the at least one starting mesh cell being outside the surface geometry of the object model and corresponding to the camera-accessible area; Iteratively expand the camera-accessible area to include adjacent mesh cells separated from the surface geometry of the object model; Elements of the surface geometry that are separated from the camera's visible area are identified as invisible elements; The following elements of the surface geometry are updated as visible elements: an unobstructed path is identified between one or more sample points on the elements of the surface geometry and the camera-accessible area; and During the rendering of an image of the object model using a virtual camera positioned within the camera's visible area, the remaining invisible elements of the surface geometry are excluded from rendering.

[0148] 2. The computer-implemented method as described in Clause 1 further includes: Before expanding the camera-accessible area, the mesh cells containing a portion of the surface geometry of the object model are identified as corresponding to a geometric region separate from the camera-accessible area.

[0149] 3. The computer-implemented method as described in Clause 1 further includes: An outer layer mesh cell is added to the virtual mesh aligned with the object model, wherein the added outer layer mesh cell includes the at least one initial mesh cell.

[0150] 4. The computer-implemented method as described in Clause 3 further includes: identifying, in parallel, multiple adjacent mesh cells that are separated from the surface geometry of the object model, based on multiple adjacent mesh cells of the camera-accessible area.

[0151] 5. The computer-implemented method as described in Clause 2 further includes: Before a given mesh cell is added to the geometry region, it is determined that a portion of the surface geometry of the object model contained in the given mesh cell is opaque.

[0152] 6. The computer-implemented method as described in Clause 1, wherein each step of the method can be executed in parallel using two or more processing units.

[0153] 7. The computer-implemented method as described in Clause 1, wherein the barrier-free path is a straight path that does not intersect with elements of the surface geometry.

[0154] 8. The computer-implemented method as described in Clause 7, wherein gaps in the surface geometry smaller than a gap size threshold are removed from the gaps considered for path consideration.

[0155] 9. The computer-implemented method as described in Clause 1 further includes: An island is defined as visible if at least one face of the island's surface geometry is determined to be visible.

[0156] 10. At least one processor, comprising one or more processing units, said one or more processing units being used for: Identify one or more mesh cells in a three-dimensional (3D) mesh that contain the surface geometry of an object model; Starting from at least one edge mesh cell outside the object model, the camera-accessible area of ​​the 3D mesh is expanded to include mesh cells of the 3D mesh that are accessible without traversing mesh cells containing the surface geometry of the object model; Path tracking is performed on one or more sample points on one or more elements of the surface geometry to identify unobstructed paths intersecting the camera's reachable area within the maximum path distance; the one or more elements corresponding to the one or more unobstructed paths are identified as visible elements; and One or more elements of the surface geometry other than the visible elements are identified as invisible elements, wherein the invisible elements are excluded from consideration in one or more subsequent operations.

[0157] 11. At least one processor as described in Clause 10, wherein the one or more processing units are further configured to: The sample points on the elements of the surface geometry are identified in part based on at least one sample interval criterion regarding the size of the grid cells.

[0158] 12. At least one processor as described in Clause 10, wherein the unobstructed path is a straight path that does not intersect with elements of the surface geometry.

[0159] 13. At least one processor as described in Clause 12, wherein gaps in the surface geometry smaller than a gap size threshold are removed from consideration for eligibility for accessibility path considerations.

[0160] 14. The at least one processor as described in Clause 10, further comprising: An island is defined as visible if at least one face of the island's surface geometry is determined to be visible.

[0161] 15. At least one processor as described in Clause 10, wherein the processor is included in at least one of: A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; Systems used to perform digital twin operations; A system for performing optical transmission simulation; A system used for rendering graphics output; A system used to perform deep learning operations; Systems implemented using edge devices; Systems used to generate or present virtual reality (VR) content; Systems used to generate or present augmented reality (AR) content; Systems used to generate or present mixed reality (MR) content; A system containing one or more virtual machines (VMs); A system that is at least partially implemented in a data center; A system for performing hardware tests using simulation; Systems for generating synthetic data; Systems for performing one or more operations using a large language model (LLM); A system for performing one or more operations using a visual language model (VLM); A system for performing one or more operations using a multimodal language model; A collaborative content creation platform for 3D assets; A system that utilizes cloud computing resources at least in part; A system that uses or deploys one or more inference microservices; or A system that combines one or more machine learning models deployed in a service or microservice with an OS-level virtualization package (such as a container).

[0162] 16. A system comprising: One or more processors are configured to identify one or more globally visible elements of an object model in part by: aligning a voxel mesh with the object model and identifying regions of camera-accessible cells, and identifying one or more visible elements of the surface geometry of the object model, wherein for at least one of the visible elements, there is at least one unobstructed path between a sample point of at least one of the visible elements and the region of the camera-accessible cell.

[0163] 17. The system as described in Clause 16, wherein the one or more processors are further configured to: The region of the camera-accessible unit is identified by starting from at least one edge cell of the voxel mesh and adding adjacent cells that do not include any elements of the surface geometry to the region of the camera-accessible unit.

[0164] 18. The system as described in Clause 17, wherein the one or more processors are further configured to: Any path from the sample point that intersects the region of the camera-accessible unit within the maximum path distance but does not intersect any element of the surface geometry is identified as the barrier-free path.

[0165] 19. The system as described in Clause 16, wherein the one or more processors are further configured to: An island is defined as visible if at least one face of the island's surface geometry is determined to be visible.

[0166] 20. The system as described in Clause 16, wherein the system comprises at least one of the following: A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; Systems used to perform digital twin operations; A system for performing optical transmission simulation; A system used for rendering graphics output; A system used to perform deep learning operations; Systems implemented using edge devices; Systems used to generate or present virtual reality (VR) content; Systems used to generate or present augmented reality (AR) content; Systems used to generate or present mixed reality (MR) content; A system containing one or more virtual machines (VMs); A system that is at least partially implemented in a data center; A system for performing hardware tests using simulation; Systems for generating synthetic data; Systems for performing one or more operations using a large language model (LLM); A system for performing one or more operations using a visual language model (VLM); A system for performing one or more operations using a multimodal language model; A collaborative content creation platform for 3D assets; A system that utilizes cloud computing resources at least in part; A system that uses or deploys one or more inference microservices; or A system that combines one or more machine learning models deployed in a service or microservice with an OS-level virtualization package (such as a container).

[0167] Other variations are within the spirit of this disclosure. Therefore, although the disclosed technology is readily adaptable to various modifications and alternative constructions, certain embodiments thereof are illustrated in the accompanying drawings and have been described in detail above. However, it should be understood that the disclosure is not intended to be limited to one or more specific forms disclosed, but rather, it is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of this disclosure as defined in the appended claims.

[0168] Unless otherwise stated or obviously contradicted by the context, the terms “a,” “an,” and “the,” and similar references, used in the context of describing the disclosed embodiments (particularly in the context of the appended claims), should be interpreted as encompassing both singular and plural forms, rather than as definitions of the terms. Unless otherwise stated, the terms “comprising,” “having,” “including,” and “containing” should be interpreted as open-ended terms (meaning “including, but not limited to”). The term “connection” (referring to a physical connection where not modified) should be interpreted as partially or wholly contained, attached to, or joined together, even with some intervention. Unless otherwise indicated herein, references to numerical ranges herein are intended only as a way of abbreviating each individual value falling within that range, and each individual value is incorporated into the specification as if it were separately described herein. Unless otherwise indicated or contradicted by the context, the use of the terms “set” (e.g., “item set”) or “subset” should be interpreted as a non-empty set comprising one or more members. Furthermore, unless otherwise indicated or contradicted by the context, the term "subset" of a corresponding set does not necessarily refer to an appropriate subset of the corresponding set, but rather the subset and the corresponding set can be equal.

[0169] Unless otherwise explicitly stated or clearly contradicted by the context, connective phrases such as “at least one of A, B, and C” or “at least one of A, B, and C” are understood in the context to generally refer to items, terms, etc., which can be A or B or C, or any non-empty subset of the set A, B, and C. For example, in an illustrative example of a set with three members, the connective phrases “at least one of A, B, and C” and “at least one of A, B, and C” refer to any of the following sets: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}, {A, B, C}. Therefore, such connective language is generally not intended to imply that some embodiments require the presence of at least one of A, at least one of B, and at least one of C. Additionally, unless otherwise stated or contradicted by the context, the term “multiple” indicates a plural state (e.g., “multiple items” means multiple items). The number of items in multiple items is at least two, but may be more if explicitly indicated or indicated by the context. Furthermore, unless otherwise stated or clearly understood from the context, the phrase “based on” means “at least partially based on” rather than “based on only”.

[0170] Unless otherwise stated herein or clearly contradicted by the context, the operations of the processes described herein may be performed in any suitable order. In at least one embodiment, processes such as those described herein (or variations thereof and / or combinations thereof) are executed under the control of one or more computer systems configured with executable instructions and are implemented as code (e.g., executable instructions, one or more computer programs, or one or more application programs) that is executed jointly on one or more processors via hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium, for example, in the form of a computer program comprising a plurality of instructions executable by one or more processors. In at least one embodiment, the computer-readable storage medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., propagating transient electrical or electromagnetic transmissions) but includes non-transitory data storage circuitry (e.g., buffers, caches, and queues). In at least one embodiment, code (e.g., executable code or source code) is stored on one or more non-transitory computer-readable storage media (or other memory for storing executable instructions) on which executable instructions are stored, which, when executed by one or more processors of a computer system (i.e., as a result of execution), cause the computer system to perform the operations described herein. In at least one embodiment, the set of non-transitory computer-readable storage media comprises multiple non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media lack all the code, but the multiple non-transitory computer-readable storage media collectively store all the code. In at least one embodiment, the executable instructions are executed such that different instructions are executed by different processors; for example, the non-transitory computer-readable storage media store the instructions, and the main central processing unit (“CPU”) executes some instructions while the graphics processing unit (“GPU”) executes other instructions. In at least one embodiment, different components of the computer system have separate processors, and the different processors execute different subsets of the instructions.

[0171] Therefore, in at least one embodiment, the computer system is configured to implement one or more services that perform the operations of the processes described herein, either individually or collectively, and such a computer system is configured with suitable hardware and / or software to enable the implementation of the operations. Furthermore, the computer system implementing at least one embodiment of this disclosure is a single device, and in another embodiment it is a distributed computer system comprising multiple devices operating in different ways, such that the distributed computer system performs the operations described herein, and that a single device does not perform all the operations.

[0172] The use of any and all examples or exemplary language (e.g., "such as") provided herein is intended only to better illustrate embodiments of this disclosure and does not constitute a limitation on the scope of the disclosure unless otherwise required. No language in the specification should be construed as indicating that any unclaimed element is essential to the practice of the disclosure.

[0173] All references cited in this article, including publications, patent applications and patents, are incorporated herein by reference as if each reference were individually and specifically indicated to be incorporated herein by reference and the entire contents of which are described herein.

[0174] The terms “coupled” and “connected”, and their derivatives, may be used in the specification and claims. It should be understood that these terms may not be intended to be synonyms with each other. Rather, in certain examples, “connected” or “coupled” may be used to indicate that two or more elements are in direct or indirect physical or electrical contact with each other. “Coupled” may also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0175] Unless otherwise expressly stated, it will be understood that throughout this specification, terms such as “processing,” “computing,” “determining,” etc., refer to the actions and / or processes of a computer or computing system or similar electronic computing device that process and / or convert data represented as physical quantities (e.g., electrons) in the registers and / or memory of the computing system into other data represented as physical quantities in the memory, registers, or other such information storage, transmission, or display devices of the computing system.

[0176] In a similar manner, the term "processor" can refer to any device or part of memory that processes electronic data from registers and / or memory and converts that electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" can be a CPU or a GPU. A "computing platform" can include one or more processors. As used herein, a "software" process can include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Similarly, each process can refer to multiple processes that execute instructions sequentially or intermittently, sequentially, or in parallel. The terms "system" and "method" are used interchangeably herein, provided that a system can embody one or more methods, and a method can be considered a system.

[0177] This document refers to the process of acquiring, obtaining, receiving, or inputting analog or digital data into a subsystem, computer system, or computer-implemented machine. Analog and digital data can be acquired, obtained, received, or input in various ways, such as by receiving data as a parameter to a function call or a call to an application programming interface (API). In some implementations, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data via a serial or parallel interface. In another implementation, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data from a providing entity to an acquiring entity via a computer network. Reference can also be made to providing, outputting, transmitting, sending, or presenting analog or digital data. In various examples, the process of providing, outputting, transmitting, sending, or presenting analog or digital data can be implemented by transmitting data as an input or output parameter to a function call, an API, or an inter-process communication mechanism.

[0178] While the discussion above illustrates example implementations of the described technologies, other architectures can be used to implement the described functionality and are intended to fall within the scope of this disclosure. Furthermore, although specific assignments of responsibilities have been defined above for discussion purposes, various functions and responsibilities can be assigned and divided in different ways depending on the circumstances.

[0179] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological actions, it should be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or actions described. Rather, specific features and actions are disclosed as exemplary forms for implementing the claims.

Claims

1. A computer-implemented method, comprising: Select at least one starting mesh cell of a virtual mesh aligned with the object model, the at least one starting mesh cell being outside the surface geometry of the object model and corresponding to the camera-accessible area; Iteratively expand the camera-accessible area to include adjacent mesh cells separated from the surface geometry of the object model; Elements of the surface geometry that are separated from the camera's visible area are identified as invisible elements; The following elements of the surface geometry are updated as visible elements: an unobstructed path is identified between one or more sample points on the elements of the surface geometry and the camera-accessible area; as well as During the rendering of an image of the object model using a virtual camera positioned within the camera's visible area, the remaining invisible elements of the surface geometry are excluded from rendering.

2. The computer-implemented method as described in claim 1, further comprising: Before expanding the camera-accessible area, the mesh cells containing a portion of the surface geometry of the object model are identified as corresponding to a geometric region separate from the camera-accessible area.

3. The computer-implemented method as described in claim 1, further comprising: An outer layer mesh cell is added to the virtual mesh aligned with the object model, wherein the added outer layer mesh cell includes the at least one initial mesh cell.

4. The computer-implemented method as described in claim 3, further comprising: Based on multiple adjacent grid cells within the camera's reach area, multiple adjacent grid cells that are separated from the surface geometry of the object model are identified in parallel.

5. The computer-implemented method as described in claim 2, further comprising: Before a given mesh cell is added to the geometry region, it is determined that a portion of the surface geometry of the object model contained in the given mesh cell is opaque.

6. The computer-implemented method as described in claim 1, wherein, Each step of the method can be executed in parallel using two or more processing units.

7. The computer-implemented method as described in claim 1, wherein, The barrier-free path is a straight path that does not intersect with any element of the surface geometry.

8. The computer-implemented method as described in claim 7, wherein, Gaps smaller than the gap size threshold in the surface geometry are removed from the gaps considered for path consideration.

9. The computer-implemented method as described in claim 1, further comprising: An island is defined as visible if at least one face of the island's surface geometry is determined to be visible.

10. At least one processor, comprising one or more processing units, said one or more processing units being used for: Identify one or more mesh cells in a 3D mesh that contain the surface geometry of an object model; Starting from at least one edge mesh cell outside the object model, the camera-accessible area of ​​the 3D mesh is expanded to include mesh cells of the 3D mesh that are accessible without traversing mesh cells containing the surface geometry of the object model; Path tracking is performed on one or more sample points on one or more elements of the surface geometry to identify unobstructed paths that intersect the camera-accessible area within the maximum path distance, and the one or more elements corresponding to the one or more unobstructed paths are identified as visible elements; as well as One or more elements of the surface geometry other than the visible elements are identified as invisible elements, wherein the invisible elements are excluded from consideration in one or more subsequent operations.

11. The at least one processor as claimed in claim 10, wherein, The one or more processing units are further configured to: The sample points on the elements of the surface geometry are identified in part based on at least one sample interval criterion regarding the size of the grid cells.

12. The at least one processor as claimed in claim 10, wherein, The barrier-free path is a straight path that does not intersect with any element of the surface geometry.

13. The at least one processor as claimed in claim 12, wherein, Gaps smaller than the gap size threshold in the surface geometry are removed from consideration for eligibility for accessibility path consideration.

14. The at least one processor as claimed in claim 10, further comprising: An island is defined as visible if at least one face of the island's surface geometry is determined to be visible.

15. The at least one processor as claimed in claim 10, wherein, The processor is included in at least one of the following: A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; Systems used to perform digital twin operations; A system for performing optical transmission simulation; A system used for rendering graphics output; A system used to perform deep learning operations; Systems implemented using edge devices; Systems used to generate or present virtual reality (VR) content; A system for generating or presenting augmented reality (AR) content; A system for generating or presenting mixed reality (MR) content; A system containing one or more virtual machines (VMs); A system that is at least partially implemented in a data center; A system for performing hardware tests using simulation; Systems for generating synthetic data; A system for performing one or more operations using a large language model LLM; A system for performing one or more operations using a visual language model (VLM); A system for performing one or more operations using a multimodal language model; A collaborative content creation platform for 3D assets; A system that utilizes cloud computing resources at least in part; A system that uses or deploys one or more inference microservices; or A system that combines one or more machine learning models deployed in a service or microservice with an OS-level virtualization package such as a container.

16. A system comprising: One or more processors are configured to identify one or more globally visible elements of an object model in part by: aligning a voxel mesh with the object model and identifying regions of camera-accessible cells, and identifying one or more visible elements of the surface geometry of the object model, wherein for at least one of the visible elements, there is at least one unobstructed path between a sample point of at least one of the visible elements and the region of the camera-accessible cell.

17. The system of claim 16, wherein, The one or more processors are also used for: The region of the camera-accessible unit is identified by starting from at least one edge cell of the voxel mesh and adding adjacent cells that do not include any elements of the surface geometry to the region of the camera-accessible unit.

18. The system of claim 17, wherein, The one or more processors are also used for: Any path from the sample point that intersects the region of the camera-accessible unit within the maximum path distance but does not intersect any element of the surface geometry is identified as the barrier-free path.

19. The system of claim 16, wherein, The one or more processors are also used for: An island is defined as visible if at least one face of the island's surface geometry is determined to be visible.

20. The system of claim 16, wherein, The system includes at least one of the following: A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; Systems used to perform digital twin operations; A system for performing optical transmission simulation; A system used for rendering graphics output; A system used to perform deep learning operations; Systems implemented using edge devices; Systems used to generate or present virtual reality (VR) content; A system for generating or presenting augmented reality (AR) content; A system for generating or presenting mixed reality (MR) content; A system containing one or more virtual machines (VMs); A system that is at least partially implemented in a data center; A system for performing hardware tests using simulation; Systems for generating synthetic data; A system for performing one or more operations using a large language model LLM; A system for performing one or more operations using a visual language model (VLM); A system for performing one or more operations using a multimodal language model; A collaborative content creation platform for 3D assets; A system that utilizes cloud computing resources at least in part; A system that uses or deploys one or more inference microservices; or A system that combines one or more machine learning models deployed in a service or microservice with an OS-level virtualization package such as a container.

Images