Interactive neural field editing in content generation systems and applications

Abstract

The invention discloses interactive neural field editing in content generation systems and applications. Systems and methods of the present disclosure include interactive editing of a generated three-dimensional (3D) model (e.g., a model represented by a neural radiation field (NeRF)). The 3D model may be presented to a user, where the user may identify one or more local regions for editing and / or modification. A local area may be selected, and a corresponding 3D volume of the area may be provided to one or more generative networks along with cues to generate new content for the local area. Each of the original NeRF and the NeRF of the newly generated new content may then be combined into a single NeRF to combine the 3D representation with the original content and the local modifications.

Description

Background Art

[0001] In various applications (such as, for example, gaming, animation, or virtual reality content generation), it may be beneficial (if not essential) to render complex three-dimensional (3D) objects in a manner that appears substantially realistic or at least consistent to a human viewer. Machine learning has improved the ability to generate new views of complex 3D scenes, for example by using neural radiance field (NeRF)-based methods that can render new views of 3D objects or environments using models of 3D objects generated from two-dimensional (2D) images of the objects. However, due to the underlying models used when generating these 3D objects (e.g., diffusion models intended to generate entirely new images or stylized models intended to stretch or modify properties of existing 3D objects), it may be difficult to edit or otherwise modify these generated 3D objects. These methods are not sufficient to provide targeted editing or modification of existing 3D objects, which may limit the use of such models and / or eliminate the time savings associated with these models because additional editing time is required to make targeted modifications. BRIEF DESCRIPTION OF THE DRAWINGS

[0002] Various embodiments according to the present disclosure will be described with reference to the accompanying drawings, in which:

[0003] Figure 1 An example network for object generation according to at least one embodiment is shown;

[0004] Figure 2 An example environment for object generation based on modification input in accordance with at least one embodiment is shown;

[0005] Figure 3A An example environment for selecting a three-dimensional volume according to at least one embodiment is shown;

[0006] Figure 3B An example environment for selecting a two-dimensional volume according to at least one embodiment is shown;

[0007] Figure 3C and Figure 3D An example environment for identifying a three-dimensional volume from a two-dimensional input in accordance with at least one embodiment is shown;

[0008] Figure 4A An example environment for generating content within a selected volume according to at least one embodiment is shown;

[0009] Figure 4B An example environment for generating a composite object according to at least one embodiment is shown;

[0010] Figure 5AAn example process for generating a composite object according to at least one embodiment is shown;

[0011] Figure 5B An example process for generating a composite object according to at least one embodiment is shown;

[0012] Figure 5C An example process for determining a three-dimensional volume for generating a composite object is shown in accordance with at least one embodiment;

[0013] Figure 6 Components of a distributed system that may be used to update or perform inference using a machine learning model according to at least one embodiment are shown;

[0014] Fig. 7A Inference and / or training logic according to at least one embodiment is shown;

[0015] Figure 7B Inference and / or training logic according to at least one embodiment is shown;

[0016] Figure 8 An example data center system is shown in accordance with at least one embodiment;

[0017] Fig. 9 A computer system according to at least one embodiment is shown;

[0018] Fig.10 A computer system according to at least one embodiment is shown;

[0019] Fig.11 illustrates at least a portion of a graphics processor according to one or more embodiments;

[0020] Fig.12 illustrates at least a portion of a graphics processor according to one or more embodiments;

[0021] Fig.13 is an example data flow diagram of a high-level computing pipeline according to at least one embodiment;

[0022] Fig.14 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

[0023] Fig.15A and Fig. 15B A data flow diagram of a process for training a machine learning model, and a client-server architecture for augmenting an annotation tool with a pre-trained annotation model, according to at least one embodiment are shown. DETAILED DESCRIPTION

[0024] In the following description, various embodiments will be described. For the purpose of explanation, specific configurations and details are set forth to provide a thorough understanding of the embodiments. However, it will also be appreciated by those skilled in the art that the embodiments may be implemented without the specific details. In addition, well-known features may be omitted or simplified to avoid obscuring the described embodiments.

[0025] The systems and methods described herein may be used, without limitation, by non-autonomous vehicles or machines, semi-autonomous vehicles or machines (e.g., in in-cabin infotainment or digital or driver virtual assistant applications), autonomous vehicles or machines, manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, spacecraft, boats, space shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, aircraft, construction vehicles, trains, underwater vehicles, remotely controlled vehicles (e.g., drones), and / or other vehicle types. In addition, the systems and methods described herein can be used for a variety of purposes, such as, but not limited to, machine control, machine motion, machine driving, synthetic data generation, model training or updating, perception, augmented reality, virtual reality, mixed reality, robotics, safety and supervision, simulation and digital twins, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, object or participant simulation and / or digital twins, data center processing, conversational artificial intelligence (AI), generative artificial intelligence with large language models (LLM), light transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation of 3D assets, cloud computing, and / or any other suitable application.

[0026] The disclosed embodiments may be included in a variety of different systems, such as automotive systems (e.g., control systems for autonomous or semi-autonomous machines, perception systems for autonomous or semi-autonomous machines), systems implemented using robots, aviation systems, medical systems, boating 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 including one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least in part in a data center, systems for performing conversational AI operations, systems for performing generative AI operations using LLMs, systems for performing light transport simulations, systems for performing collaborative content creation of 3D assets, systems implemented at least in part using cloud computing resources, and / or other types of systems.

[0027] Methods according to various embodiments may be used to implement local changes to one or more three-dimensional (3D) objects or scenes represented by a neural radiance field (NeRF). NeRF may be used to learn a plenoptic function (e.g., a five-dimensional (5D) function that takes a 3D space coordinate and two or more view-dependent angles as input). NeRF may be used to output a 3D radiance field of density and color of the quality of light at a given location when viewed from a specific direction and position. Thus, an object represented by NeRF may capture view-dependent effects, such as specular reflections of an object. For faster learning and rendering, NeRF may be represented or visualized as a voxel grid, where features are stored at the corners of the voxels (e.g., using an octree as a non-limiting example). Unlike representations using a mesh with faces and vertices, NeRF uses coordinates in 3D space, a view direction, and lighting and color information for the coordinates. NeRF may be implemented as a machine learning model that receives input parameters (e.g., coordinates in 3D space, a view direction, lighting, and color) and uses these parameters to output an image of a scene, and one or more diffusion models may be used to train NeRF to generate an associated representation. NeRF can be combined or used with generative AI solutions (such as diffusion models) that can receive input or prompts (e.g., text, audio, images, etc.) to generate images. However, NeRF, and by extension, images generated using NeRF, are difficult to edit locally. For example, a user may want to select a portion of a scene represented by NeRF to add additional details or enhance the way NeRF represents an object. Unlike style changes that stretch or distort the original underlying features, the systems and methods of the present disclosure are intended to generate new content, such as edited or modified NeRF, which can be mixed with the original NeRF to form a new 3D representation. In at least one embodiment, a user can provide a first input corresponding to a selection of a 3D volume portion of the scene to be modified. For example, a user can select a 2D area based on a camera perspective with optional features to correspond to a selected 3D depth, such as a period of time, multiple selections from different views, or other options. Then, in an embodiment using a diffusion model, the user can provide a second input corresponding to a prompt associated with the content of the selected area. The system can then use one or more models (e.g., a text-to-image model) to generate 3D content for the selected 3D volume associated with the first input. Thereafter, the original NeRF can be blended with the newly generated NeRF using different methods to create a modified NeRF. Various blending techniques can be used, such as replacing different features with different voxel representations within the NeRF, concatenating features between two NeRFs, and so on.

[0028] The systems and methods may be implemented as part of a content generation pipeline. The pipeline may include a diffusion model for optimizing NeRF to generate 3D images, although other models may be used within the scope of the present disclosure. A decoder associated with the diffusion model may be used to present the generated NeRF to a user, which may then be used in an interactive environment to allow selection of different volumes of NeRF that may be fed back into the diffusion model or into one or more other diffusion models or other generative models to generate a new NeRF for a selected region. The user may iterate with different inputs and selections, such as generating new content for a first NeRF region and generating different new content for a second NeRF region, thereby generating a combined NeRF to provide a 3D scene representation including one or more objects or objects with enhancements, etc.

[0029] There are many different operations or use cases in which image content including one or more objects is to be generated, for example, one or more foreground objects and one or more background objects. These "objects" may include digital representations of physical or virtual objects, which can be used to generate images showing views of the objects from various positions of a virtual camera. The objects in at least one embodiment may be explicit digital assets. In addition, other types of objects may be used to generate images of scenes. This may include, for example, views of one or more objects, volumetric data representations, or other implicit representations. These implicit representations may be generated by neural networks such as fully connected NeRF networks. As previously described, NeRF can be used to generate novel views of objects from any appropriate viewpoint. NeRF reasoning typically involves calculating the radiance and density at a given 3D position of a scene, which may include integrating ray segments and outputting different extended data, such as surface normals, segmentation identifiers, material parameters, or 3D motion data. Within the scope of various embodiments, various other ways may also be used to generate, provide, or render digital objects (or views of these objects). However, as described above, it may be difficult to combine or synthesize these different types of images into a single image or common scene. These difficulties may become more apparent when considering other aspects of a given virtual environment, such as lighting, particularly with respect to secondary lighting effects such as shadows, reflections, or other such indirect and / or diffuse lighting effects.

[0030] Figure 1An example pipeline 100 is shown that can be used to generate an object 102 (e.g., an object that forms at least a portion of a scene). A set of images 104 can be used to train a NeRF network 106 (e.g., a NeRF model) (which can include one or more diffusion models) to generate different output objects, such as outputs based on input prompts or requests. For example, the images can be one or more objects or scenes taken from different perspectives. The position and direction of the perspective can be calculated and used to train the network. In this example, the NeRF network 106 includes one or more neural networks, such as multi-layer perceptrons (MLPs), but it should be understood that other networks can be incorporated into the NeRF network 106 and / or can be accessed by the NeRF network 106. For example, one or more LLMs can be associated with the NeRF network 106 to receive and process input prompts. The NeRF network 106 can be used to generate data associated with color 108 and volume density 110, which can be provided to a renderer 112 for generating an object 102, such as a 3D representation of the object 102.

[0031] The object 102 represented by NeRF may be different from a typical representation using a mesh-based approach, but NeRF can be converted to a mesh using various operations (e.g., the marching cube method). Meshes typically include faces and vertices, and therefore may be difficult to manipulate because different networks are required to estimate or otherwise determine the appropriate number of faces and vertices to provide a discrete representation of the object. On the other hand, NeRF is a neural representation of how different points look from a given camera perspective, and therefore lacks the faces and vertices common to mesh representations.

[0032] Figure 2 An example pipeline 200 that may be used with embodiments of the present disclosure is shown. In this example, the pipeline 200 may represent the generation of content, such as one or more 3D objects, using a NeRF network 106, which may include one or more diffusion models and one or more NeRF decoders in this example, and then locally modifying the output of the NeRF network 106 to generate a composite object that includes features of the original object and additional features resulting from one or more edits / modifications. In this example, an input 202 is provided to the NeRF network 106, and the input 202 may include text input (e.g., using text to a 3D model, which may be a diffusion model, as a non-limiting example) or various other commands. In addition, the NeRF network 106 may be trained to output certain types of objects, and thus, the input 202 may be a command to output certain objects based on the training without requiring specific instructions related to the features of the object.

[0033] The NeRF network 106 may pass information such as color and volume density to the renderer 112, which may provide the object 102 for viewing within the interactive environment 204. Although the NeRF network 106 and other features are shown as being outside the interactive environment 204, various embodiments may include the NeRF network 106 and various other features as part of the interactive environment 204. A user may view the object 102 within the interactive environment 204 and determine that one or more modifications would be desirable. In some embodiments, the modification may be a local modification applied to one or more singular features or regions of the object 102 rather than to the entire object. For example, a user may wish to add additional components to the object 102 to build a scene around the object. For example, the object 102 may correspond to a car, and the user may wish to add rocks around the car to make the car appear to be on the edge of a cliff. In order to improve the accuracy of the output rendering, the user may wish to make certain parts of the rock appear to be in front of the car, behind the car, under the car, etc. Current models are unable to provide such fine-tuning and localized editing. Instead, the user needs to provide guiding cues to the NeRF network 106 and hope that the newly generated output corresponds to the desired layout.The disclosed systems and methods address this and other shortcomings of existing systems by providing localized editing and modification of the output of a NeRF network.

[0034] In this example, input 202 may be provided to the NeRF network 106 by a user or through one or more systems (e.g., systems as part of a workflow). For example, a computing device may include stored software instructions that submit requests to the NeRF network 106 in response to one or more triggers or commands, which may be automatic commands or commands received in response to additional actions or inputs from one or more users. In addition, input 202 may include prompts or other requests submitted by users (e.g., users associated with the interactive environment 204). The NeRF network 106 may be used to generate one or more features that are rendered for display within the interactive environment 204, such as using a renderer 112, and may then be further edited and / or manipulated by a user or computing device interacting with the interactive environment 204. For example, modification input 206 may be provided to an editor 208 associated with the interactive environment 204. The editor 208 may include one or more tools to enter options to facilitate receiving the modification input 206. For example, the editor 208 may include different selection devices to allow a user to select specific areas or features of an object, specialized tools for making specific modifications, and the like.

[0035] In at least one embodiment, the modification input 206 can be associated with the selection of one or more areas or regions of the object 102 for modification and / or adjustment. For example, a user can interact with the object 102 from a camera view perspective and then select one or more areas using input commands, such as highlighting an area of ​​the object 102 from a given camera view perspective or graffiti on an area of ​​the object 102, as well as other options. The user and / or device can also provide additional commands, which can be provided back to the NeRF network 106 to generate additional objects associated with the modification input 206. By the way shown, the modification input 206 can include multiple parts. For example, the first part of the modification input 206 can be associated with an area or part of the object 102, and the second part can be a prompt or command to be provided to the NeRF network 106 to generate additional objects. In the example of a car and the desired addition of rocks, the first part of the modification input 206 can include an indication of the location to place the rock, such as the user marking, graffiti, clicking, etc. in the desired area, and the second part of the modification input 206 can include a "small rock on the ground" for the NeRF network 106 to use to generate additional content.

[0036] As described herein, the modification input 206 may be provided to the editor 208 and / or may also be provided to the NeRF network 106, such as by dividing different portions of the modification input 206 to go to different locations. In at least one embodiment, the area identified by the user or computing device may be used to bound or otherwise limit new content generated by the NeRF network 106. For example, content may be developed within the boundaries associated with the first portion of the modification input, such as due to a mask generated for a particular selected area. A modification object 210 (e.g., modification output) may be generated by the NeRF network 106, which may be a generated output later used by a component of the interactive environment 204 and / or may be provided to the renderer 112 for display within the interactive environment 204, such as by the renderer 112. Figure 2 In some embodiments, the user may wish to visualize and see the modifications before adding them to the original object 102. However, in other embodiments, the user may wish to see the combination of the object 102 and the modified object 210 before making additional adjustments or modifications.

[0037] Various embodiments may include a mixer 212 for splicing or otherwise combining a modified object 210 (or several modified objects 210) with an object 102 to form a combined object 214. The mixer 212 may be used to mask one or both of the object 102 and the modified object 210, and then combine the different NeRFs for each related object. For example, a mask may be associated with a portion of the modified input 206 so that areas outside the identified area are masked for the NeRF of the object 102, and the modified object 210 is confined to the area identified by the modified input 206. In this way, two (or more) NeRFs may be combined via the mixer 212 to produce the combined object 214. In another example, an identified area of ​​a first object may be filled with a new object. In another example, feature values ​​of a first object may be replaced with feature values ​​of a second object for a given area. In another example, a palette may be mixed to generate a combined NeRF. Thus, various embodiments of the present disclosure may combine two NeRFs into a single output representation using one or more different operations. As described herein, in various embodiments, the mixer 212 may also return information to the renderer 112 to render the combined object 214 within the interactive environment 204 and / or may include its own renderer, or may combine already rendered objects, as mentioned herein.

[0038] Thus, the systems and methods of the present disclosure may be used to generate a composite object 214 in which portions of one or more NeRF objects 102, 210 have been combined to provide a localized edit to the object 102. The modification input 206 may be used to specifically identify an area of ​​the object 102 to be modified, and / or tools associated with the editor 208 may be used to add certain components or features that are specific to a particular tool. By way of example, a tool may be provided for a particular environment or scene setting, such as a tool for adding trees to an outdoor scene or a tool for adding furniture to an indoor scene. In this way, specific areas of the generated object may be edited without completely regenerating the object and / or modifying the initial prompt with the required additional information. The systems and methods may also allow objects or scenes to be built on separate areas each associated with a modification input. For example, a first area of ​​a scene may have a first object, a second area may include a modification or adjustment to the first object, a third area may include a second object, and so on, until the entire scene is built from multiple objects that blend different NeRFs together. In at least one embodiment, when further modifications are made to the composite object, the original NeRF is discarded or otherwise not used, so that new modifications and blends are between the new modifications and the composite object. In other embodiments, each NeRF is maintained separately and then combined after editing is complete.

[0039] Figure 3A and Figure 3BExample environments 300, 320 are shown for applying one or more modification inputs 206 with varying interfaces. For example, environment 300 may be arranged as a 3D volume composed of primitives, while environment 320 may be arranged as a 2D brush or mask that may be applied from a given view. Figure 3A 300, an object 302 is represented as a NeRF corresponding to a front-end loader made of building blocks. The object 302 is provided as a non-limiting example and may also include various other objects and / or scenes. In addition, the object 302 may be formed of different individual components, such as in this example, the tracks, the frame on which the tracks are located, the cab, the bucket, etc. A virtual camera 304 corresponding to the perspective of the object 302 is provided. The perspective in this environment shows a consistent segmentation map 306, which is represented as volumes (e.g., cubes) corresponding to different 3D dimensions / parts of the object 302. For example, each volume 308 includes a height 310 (e.g., 3D height), a width 312 (e.g., 3D width), and a depth 314 (e.g., 3D depth). The size of a given volume 308 is provided for clarity of this discussion, and the volume may be larger or smaller, and the size of different areas may be different. Selecting one or more volumes 308 may provide a selection of the entire volume (e.g., height, width, and depth). That is, the selection will define a given 3D area that can be optimized and / or used to modify the input.

[0040] In this example, selection is indicated by shading volume 308, for example, by a user giving input for a different region. The size of volume 308 may vary. Figure 3A , such as smaller or larger, or may have different sizes for different areas of object 302, such as smaller volumes for finer details and larger volumes for larger open spaces. The modification input may then include selecting one or more volumes 308 and providing a prompt to generate the modification within the volume, which may include text input, selection to use a particular tool, and / or the like. Thus, a user or device may interact with object 302 in 3D space to define different 3D areas to generate different objects to blend with object 302.

[0041] Figure 3BRepresenting an environment 320, where a 2D mask can be transformed into a 3D region, as described herein. In this example, a user can provide modification input using one or more tools (e.g., a brush tool or a doodle tool) where certain 2D portions of object 302 are "painted" or "marked" or otherwise identified. The tool can also be associated with a specific type of modification, such as modifications that may be common for a given scene. For example, if many scenes of a particular set of objects are associated with outdoor scenes, there may be a brush or stamp tool associated with common objects in outdoor scenes (e.g., rocks, grass, trees, etc.). By selecting one of the particular tools, a prompt or other information for the NeRF network can be pre-selected, thereby simplifying the user's operation.

[0042] As described herein, the NeRF of object 302 is a three-dimensional representation, but Figure 3B Embodiments are directed to using 2D associations to draw or otherwise mark area 322. Thus, the systems and methods of the present disclosure may implement one or more features to obtain depth information about the modification input. For example, in at least one embodiment, a ray may be generated via a 2D brush or from the input and traced against a feature grid. Thereafter, "marching" into the plane of object 302 may be stopped once the sample density is saturated. In other embodiments, user input may provide an indication of depth, such as a user holding down a mouse click longer to move farther into the depth of object 302. In other embodiments, depth may be provided as another modification input and / or may be a text-based prompt. About Figure 3B The object 302 may be aimed at area 322 as shown, and the text prompt may then include further instructions, such as "behind the track" or "behind the front loader." Thus, the 2D input may be transformed to enable 3D generation of new content to blend with the object 302.

[0043] Figure 3C Shown with Figure 3B 320, wherein a three-dimensional region of a volume 308 is identified by ray tracing from an initial input region 322. In this example, a virtual camera 304 is shown with the region 322 represented on a 2D plane 342. A series of rays 344 are then emitted from the virtual camera 304 and traverse the region to intersect the volume 308 associated with an object (not shown). Each volume 308 "hit" by one of the rays 344 may then be marked for further evaluation.

[0044] Figure 3DA representation 360 of a marked volume 308 based on the interaction between a ray 344 and a representation of an object is shown, shown as shaded. In this example, the different volumes can be evaluated as being close relative to a line 362 representing the camera position, or at a saturation depth relative to a line 364 associated with one or more parameters to determine the depth of the 2D region 322. For example, as mentioned herein, the depth can be determined using the length of time a mouse click is held, an input value, etc. Each corner of the different volumes 308 includes a feature node, represented as a circle 366. The feature node can be an octree, but other representations can be used within the scope of the present disclosure. By tracing rays and making depth determinations, the initial 2D input of the region 322 can be converted to a 3D volume, which can then be used to generate a NeRF object for blending with the original object.

[0045] Figure 4A A representation 400 of an input volume 402 from a modification input is shown, which is provided to the NeRF network 106 for use in the generation of the modification object 210. In this example, the 3D volume corresponds to the input volume 402, which may be generated from a 2D input (e.g., Figure 3B ) or 3D input (as Figure 3A The input volume 402 may be viewed from a plurality of different camera positions 404 for processing by the NeRF network 106. In this example, the modified input also includes a prompt 406, such as in a text-based system where a user or device may provide a text prompt, which the NeRF network 106 then uses to generate an output based on the prompt. Figure 4A Hint 406 may correspond to "grass" such that modified object 210 corresponds to grass within the volume defined by input volume 402. As mentioned herein, hint 406 may also be associated with a tool used to form input volume 402. For example, a brush defined as a "grass brush" will also provide an appropriate hint for generating modified object 210.

[0046] Figure 4BA pipeline 420 is shown, which can represent the modification of a generated 3D object (e.g., a NeRF object). In this example, an input 202 is provided to a NeRF network 106, which, as mentioned herein, can be used to generate one or more objects or scenes, which in this example is a front-end loader. As shown, the input 202 can include a prompt, such as a text prompt in some examples, which can guide or otherwise instruct the NeRF network 106 about the output object 102. The object 102 can be presented for editing, such as in an interactive environment, and a user can provide a modification input 206, indicating one or more areas or regions of the object 102 to be modified. As described herein, the modification can be represented in 2D or 3D, wherein the 2D modification can be converted to a 3D volume, and a specific area can be provided back to the NeRF network 106 for further generation of one or more modified objects 210, in this example the modified object 21 is "grass". As shown, the modified object 210 can conform to the shape of the modified input 206, such as conforming to the volume extracted from the modified input 206.

[0047] In at least one embodiment, each of the object 102 and the one or more modified objects 210 can be processed by the mixer 212 to form a combined object 214. For example, the mixer 212 can be used to form a mask, such as the mask 422, on portions of the object 102 and / or the modified object 210. The mask 422 can correspond to areas that will not be replaced or areas that will be replaced. The mixer 212 can then combine the associated NeRFs of the object 102 and the modified object 210 to form the combined object 214. For example, the modified object 210 can be linked to the unmasked area of ​​the object 102. In another example, feature values ​​are compared and replaced between the object 102 and the modified object 210. Thus, two separately generated objects can be blended together to form a single representation.

[0048] Figure 5AAn example process 500 is shown that can be used to generate a combined NeRF. It should be understood that for this process and other processes described herein, there may be additional, fewer, or alternative operations that are performed in a similar or alternative order or at least partially in parallel within the scope of various embodiments, unless otherwise explicitly stated. In addition, while this example relates to NeRF and using prompts, generating content using a diffusion model, it should be understood that various other such tasks can benefit from aspects of such a training process, which are well within the scope of various embodiments, and various different model representations and / or generative models may also be used. In this example, a selected portion of a 3D volume for a first NeRF is received 502. For example, the selected portion can be identified by a user or a device through an interface and can be associated with one or more desired edits or modifications to the NeRF. As described herein, the 3D volume can be identified by a user, or can be determined based on a user selection in 2D space and additional input and / or a determination of depth to provide a 3D volume. In at least one embodiment, a prompt corresponding to a content request 504 can be received. The prompt can be a text prompt or a converted text prompt (e.g., an auditory prompt converted to text). Additionally, certain features associated with a tool that provides a modification input may also be associated with a hint, such as a hint designed for a particular type of output (e.g., "grass brush"). A second NeRF may be generated within the selected volume based on the hint 506. For example, one or more diffusion models may receive the hint and then generate content within the boundaries of the volume. An output NeRF may then be formed by combining features of the original NeRF and the newly generated NeRF 508, thereby creating a combined output in which the originally generated object has been selectively modified.

[0049] Figure 5B An example process 520 is shown that can be used to generate a scene represented as a NeRF. In this example, the scene representation is generated as a NeRF 522. In at least one embodiment, one or more diffusion models are used to generate a scene represented in a 3D space, which can include one or more objects. An input corresponding to a portion of a NeRF 524 can be received. For example, a user can receive an original NeRF and provide input corresponding to a location where a local edit is applied. In addition, the input can include a prompt or can be associated with a relevant prompt. A modified NeRF can be generated using the prompt, and the modified NeRF includes one or more new content portions compared to the original NeRF 526. The original NeRF and the modified NeRF can then be combined 528, such as by replacing segments, overlapping portions, adjusting a color palette, etc., to generate an updated NeRF, including content from the original NeRF and content from the modified NeRF.

[0050] Figure 5CAn example process 540 for generating a combined representation is shown. In this example, an input corresponding to a 3D representation of an object region is received 542. The region can be selected from a generated 3D object, which can be represented by NeRF and can also correspond to a region where one or more modifications or additions need to be made. The volume of the region can be determined 544, which can be based on at least one or more first attributes of the input. For example, the input can include a selection from a 3D viewing space, where certain volumes are specifically selected. In another example, a 2D region can be selected, and then the volume can be determined using attributes associated with the depth of the selection. In at least one embodiment, a target object can be determined 546, which can be based on at least one or more second attributes of the input. For example, the input can be accompanied by a text prompt or a tool associated with a particular target object, as well as other options. The input can be used to generate a target object within a volume 548, and then the target object within the volume can be combined with the original representation to generate a combined representation 550.

[0051] As discussed, aspects of the various methods described herein can be lightweight enough to be performed in real time on a device such as a client device such as a personal computer or a gaming console. Such processing can be performed on or for content generated on or received by the client device or content received from an external source, such as streaming data or other content received over at least one network. In some cases, the processing and / or determination of the content can be performed by one of these other devices, systems, or entities and then provided to the client device (or another such recipient) for presentation or another such use.

[0052] As an example, Figure 6An example network configuration 600 is shown that can be used to provide, generate, modify, encode, process and / or transmit image data or other such content. In at least one embodiment, a client device 602 can generate or receive data for a session using components of a control application 604 on the client device 602 and data stored locally on the client device. In at least one embodiment, a content application 624 executed on a server 620 (e.g., a cloud server or an edge server) can initiate a session associated with at least one client device 602, can utilize a session manager and user data stored in a user database 636, and can cause a content manager 626 to determine content from an asset repository 634, such as one or more digital assets (e.g., object representations). The content manager 626 can collaborate with an image synthesis module 628 to generate or synthesize new objects, digital assets, or other such content to be provided for presentation by the client device 602. In at least one embodiment, the image synthesis module 628 can use one or more neural networks or machine learning models that can be trained or updated using a training module 632 or system located on or in communication with the server 620. This may include training and / or using a diffusion model 630 to generate content tiles that may be used by an image synthesis module 628, e.g., applying a non-repeating texture to an area of ​​an environment where image or video data is to be presented by a client device 602. At least a portion of the generated content may be transmitted to the client device 602 using an appropriate transmission manager 622 to be sent via download, streaming, or another such transmission channel. An encoder may be used to encode and / or compress at least a portion of the data before transmitting at least a portion of the data to the client device 602. In at least one embodiment, a client device 602 receiving such content may provide the content to a corresponding control application 604, which may also or alternatively include a graphical user interface 610, a content manager 612, and an image synthesis or diffusion module 614 for providing, synthesizing, modifying, or using content for presentation on or by the client device 602 (or other purposes). The decoder may also be used to decode data received via the network 640 for presentation via the client device 602, such as images or video content presented via a display 606 and audio (e.g., sounds and music) presented via at least one audio playback device 608 (e.g., speakers or headphones). In at least one embodiment, at least a portion of the content may already be stored on the client device 602, rendered on the client device 602, or accessible to the client device 602, such that at least the portion of the content does not need to be transmitted via the network 640, such as the content may have been previously downloaded or stored locally on a hard disk or optical disk.In at least one embodiment, the content may be transmitted from the server 620 or user database 636 to the client device 602 using a transmission mechanism (e.g., data streaming). In at least one embodiment, at least a portion of the content may be obtained, enhanced, and / or streamed from another source (e.g., a third-party service 660 or another client device 650), which may also include a content application 662 for generating, enhancing, or providing the content. In at least one embodiment, multiple computing devices or multiple processors within one or more computing devices (e.g., which may include a combination of CPUs and GPUs) may be used to perform portions of this functionality.

[0053] In this example, these client devices may include any appropriate computing devices, such as desktop computers, laptops, set-top boxes, streaming devices, game consoles, smartphones, tablet computers, VR headsets, AR goggles, wearable computers, or smart TVs. Each client device may submit a request across at least one wired or wireless network, which may include the Internet, Ethernet, a local area network (LAN), or a cellular network, as well as other such options. In this example, these requests may be submitted to an address associated with a cloud provider, which may operate or control one or more electronic resources in a cloud provider environment, such as a data center or a server farm. In at least one embodiment, the request may be received or processed by at least one edge server located at the edge of the network and outside of 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 that are closer, while also improving the security of resources in the cloud provider environment.

[0054] In at least one embodiment, such a system may be used to perform graphics rendering operations. In other embodiments, such a system may be used for other purposes, such as for providing image or video content to test or verify autonomous machine applications, or for performing deep learning operations. In at least one embodiment, such a system may be implemented using an edge device, or may be combined with one or more virtual machines (VMs). In at least one embodiment, such a system may be implemented at least in part in a data center or at least in part using cloud computing resources.

[0055] Reasoning and training logic

[0056] Fig. 7A Inference and / or training logic 715 is shown for performing reasoning and / or training operations associated with one or more embodiments. Fig. 7A and / or Figure 7B Details regarding the inference and / or training logic 715 are provided.

[0057] In at least one embodiment, the 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 for configuring neurons or layers of a neural network trained and / or used for inference in aspects of one or more embodiments. In at least one embodiment, the 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, where weights and / or other parameter information is loaded to configure logic, including integer and / or floating point units (collectively referred to as arithmetic logic units (ALUs)). In at least one embodiment, the code (such as graph code) loads weights or other parameter information into a processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, the code and / or data storage 701 stores input / output data during training and / or inference using aspects of one or more embodiments and / or weight parameters during forward propagation of each layer of a neural network trained or used in conjunction with one or more embodiments. In at least one embodiment, any portion of code and / or data storage 701 may be included within other on-chip or off-chip data storage, including a processor's L1, L2, or L3 cache or system memory.

[0058] In at least one embodiment, any portion of 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, code and / or data storage 701 may be 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 code and / or data storage 701 is internal or external to a processor, for example, or consists of DRAM, SRAM, flash memory, or some other storage type, may depend on the available storage space on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the batch size of the data used in inference and / or training of the neural network, or some combination of these factors.

[0059] 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 reverse 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 aspects of one or more embodiments. In at least one embodiment, during training and / or inference using aspects of 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 conjunction with one or more embodiments during back propagation 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 weights and / or other parameter information is loaded to configure logic including integer and / or floating point units (collectively referred to as arithmetic logic units (ALUs)). In at least one embodiment, code (such as graph code) loads weights or other parameter information into a processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, any portion of 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. In at least one embodiment, any portion of 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, 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 of whether code and / or data storage 705 is internal or external to the processor, for example, whether it is composed of DRAM, SRAM, flash memory, or some other storage type, 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.

[0060] 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 the same storage structure 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.

[0061] 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 based at least in part on or as directed by training and / or inference code (e.g., graph code), the results of which may produce activations (e.g., output values ​​from a layer or neuron within a neural network) stored in activation storage 720, which is a function 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, activations are performed in response to executing instructions or other code, linear algebra and / or matrix-based mathematics performed by ALU 710 to generate activations stored in activation storage 720, where weight values ​​stored in code and / or data storage 705 and / or in 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, any or all of which may be stored in code and / or data storage 705 or code and / or data storage 701 or other on-chip or off-chip storage.

[0062] In at least one embodiment, one or more ALUs 710 are included in one or more processors or other hardware logic devices or circuits, while in another embodiment, one or more ALUs 710 may be outside a processor or other hardware logic device or circuit that uses 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 an execution unit of a processor, which may be within the same processor or distributed between 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 circuit, while in another embodiment, they may be in different processors or other hardware logic devices or circuits or some combination of the same and different processors or other hardware logic devices or circuits. In at least one embodiment, any portion of activation storage 720 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Additionally, inference and / or training code may be stored with other code accessible to a 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.

[0063] In at least one embodiment, activation storage 720 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, activation storage 720 may be completely or partially internal or external to one or more processors or other logic circuits. In at least one embodiment, activation storage 720 may be selected to be internal or external to a processor, for example, or include DRAM, SRAM, flash memory, or other storage types, depending on the storage available on-chip or off-chip, the latency requirements for performing training and / or inference functions, the batch size of data used in inferencing and / or training neural networks, or some combination of these factors. In at least one embodiment, Fig. 7A The inference and / or training logic 715 shown in FIG. 7 may be used in conjunction with an application specific integrated circuit (“ASIC”), such as the ASIC from Google. Processing unit from Graphcore TM Inference Processing Unit (IPU) from Intel Corp (e.g., "LakeCrest") processor. In at least one embodiment, Fig. 7A The illustrated inference and / or training logic 715 may be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware such as a field programmable gate array (“FPGA”).

[0064] Figure 7B Inference and / or training logic 715 is shown in accordance with at least one or more embodiments. In at least one embodiment, the reasoning and / or training logic 715 may include, but is not limited to, hardware logic in which computing 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 in FIG. 7 may be used in conjunction with an application specific integrated circuit (ASIC), such as the ASIC from Google. Processing unit from Graphcore TM Inference Processing Unit (IPU) from Intel Corp (e.g., "LakeCrest") processor. In at least one embodiment, Figure 7BThe inference and / or training logic 715 shown in 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 in , each of code and / or data storage 701 and code and / or data storage 705 is associated with a dedicated computing resource (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) solely on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, and the results of performing the functions are stored in activation storage 720.

[0065] In at least one embodiment, each of the code and / or data stores 701 and 705 and the corresponding computing hardware 702 and 706 corresponds to a different layer of the neural network, such that activations from one "storage / compute pair 701 / 702" of the code and / or data store 701 and computing hardware 702 are provided as inputs to the next "storage / compute pair 705 / 706" of the code and / or data store 705 and computing hardware 706, so as to reflect the conceptual organization of the neural network. In at least one embodiment, each storage / compute pair 701 / 702 and 705 / 706 can correspond to more than one neural network layer. In at least one embodiment, additional storage / compute pairs (not shown) can be included in the inference and / or training logic 715 after or in parallel with the storage / compute pairs 701 / 702 and 705 / 706.

[0066] Data Center

[0067] Figure 8 An example data center 800 is shown in which at least one embodiment may be used. 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.

[0068] In at least one embodiment, Figure 8As shown, the data center infrastructure layer 810 may include a resource coordinator 812, grouped computing resources 814, and node computing resources ("node CRs") 816(1)-816(N), where "N" represents any positive integer. In at least one embodiment, the node CRs 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 memories), 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 of the node CRs 816(1)-816(N) may be a server having one or more of the above computing resources.

[0069] In at least one embodiment, the grouped computing resources 814 may include a separate grouping (not shown) of node CRs housed in one or more racks, or many racks (also not shown) housed in data centers at various geographic locations. The separate grouping of node CRs within the grouped computing resources 814 may include computing, networks, memory, or storage resources that can be configured or allocated to support groupings of one or more workloads. In at least one embodiment, several node CRs including a CPU or processor may be grouped in 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.

[0070] In at least one embodiment, resource coordinator 812 may configure or otherwise control one or more node CRs 816(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 812 may include hardware, software, or some combination thereof.

[0071] In at least one embodiment, Figure 8As shown, the 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, the framework layer 820 may include a framework that supports software 832 of the software layer 830 and / or one or more applications 842 of the application layer 840. In at least one embodiment, the software 832 or the application 842 may include a web-based service software or application, such as a service or application provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, the framework layer 820 may be, but is not limited to, a free and open source software network application framework, such as Apache SparkTM (hereinafter referred to as "Spark") that can utilize the distributed file system 828 for large-scale data processing (e.g., "big data"). In at least one embodiment, the job scheduler 832 may include a Spark driver to facilitate scheduling of workloads supported by various layers of the data center 800. In at least one embodiment, the configuration manager 824 may be able to configure different layers, such as the software layer 830 and the framework layer 820 including Spark and a distributed file system 828 for supporting large-scale data processing. In at least one embodiment, the resource manager 826 can manage cluster or group computing resources mapped to or allocated to support the distributed file system 828 and the job scheduler 822. In at least one embodiment, the cluster or group computing resources can include group computing resources 814 on the data center infrastructure layer 810. In at least one embodiment, the resource manager 826 can coordinate with the resource coordinator 812 to manage these mapped or allocated computing resources.

[0072] 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 node CRs 816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. The 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.

[0073] In at least one embodiment, one or more applications 842 included in the application layer 840 may include one or more types of applications used by at least a portion of the node CRs 816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. The 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.

[0074] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource coordinator 812 can implement any number and type of self-modification actions based on any number and type of data acquired in any technically feasible manner. In at least one embodiment, the self-modification actions can relieve a data center operator of the data center 800 from making potentially bad configuration decisions and can avoid underutilized and / or poorly performing portions of the data center.

[0075] In at least one embodiment, the data center 800 may include tools, services, software, or other resources to train one or more machine learning models or 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 may be trained by calculating weight parameters according to a neural network architecture using the software and computing resources described above with respect to the data center 800. In at least one embodiment, by using weight parameters calculated by one or more training techniques described herein, information may be inferred or predicted using trained machine learning models corresponding to one or more neural networks using the resources described above with respect to the data center 800.

[0076] In at least one embodiment, the data center can use a CPU, an application-specific integrated circuit (ASIC), a GPU, an FPGA, or other hardware to use the above resources to perform training and / or reasoning. In addition, one or more of the above software and / or hardware resources can be configured as a service to allow users to train or perform information reasoning, such as image recognition, speech recognition, or other artificial intelligence services.

[0077] Reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. Fig. 7A and / or Figure 7BProvides details about the reasoning and / or training logic 715. In at least one embodiment, the reasoning and / or training logic 715 may be implemented in the system Figure 8 for use in a system for performing inference or prediction operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0078] Such components can be used for object creation and modification.

[0079] Computer Systems

[0080] Fig. 9 900 is a block diagram illustrating an exemplary computer system according to at least one embodiment, which may be a system of 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 the present disclosure, such as the embodiments described herein, the computer system 900 may include, but is not limited to, components, such as a processor 902, whose execution unit includes logic to execute algorithms for processing data. In at least one embodiment, the computer system 900 may include a processor, such as a processor available from Intel Corporation of Santa Clara, California. Processor family, Xeon TM , XScale TM and / or StrongARM TM , Core TM or Nervana TM microprocessor, although other systems (including PCs with other microprocessors, engineering workstations, set-top boxes, etc.) may also be used. In at least one embodiment, computer system 900 may execute a version of the WINDOWS operating system available from Microsoft Corporation of Redmond, Wash., although other operating systems (e.g., UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0081] Embodiments may be used in other devices, such as handheld devices and embedded applications. Some examples of handheld devices include cellular phones, Internet Protocol (Internet Protocol) 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, 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.

[0082] 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 reasoning 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 multi-processor 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 that implements an 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 may transmit data signals between the processor 902 and other components in the computer system 900.

[0083] 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. Other embodiments may also include a combination of internal and external caches, depending on the particular implementation and needs. 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.

[0084] In at least one embodiment, logic execution unit 908 that performs integer and floating point operations is also located in processor 902, including, but not limited to. In at least one embodiment, processor 902 may also include a microcode ("ucode") read-only memory ("ROM") for storing microcode for certain macroinstructions. In at least one embodiment, execution unit 908 may include logic for processing a packed instruction set 909. In at least one embodiment, by including a packed instruction set 909 in the instruction set of a general purpose processor, and associated circuitry to execute the instructions, operations used by many multimedia applications may be performed using packed data in processor 902. In one or more embodiments, many multimedia applications may be executed faster and more efficiently by using the full width of the processor's data bus to perform operations on packed data, which may not require the transfer of smaller units of data on the processor's data bus to perform one or more operations one data element at a time.

[0085] In at least one embodiment, execution unit 908 may also be used in microcontrollers, embedded processors, graphics devices, DSPs, and other types of logic circuits. 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 may be executed by processor 902.

[0086] In at least one embodiment, the system logic chip can be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip can include, but is not limited to, a memory controller hub ("MCH") 916, and the processor 902 can communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 can provide a high-bandwidth memory path 918 to the memory 920 for instruction and data storage and for storage of graphics commands, data, and textures. In at least one embodiment, the MCH 916 can 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 can provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 can be coupled to the memory 920 via a high-bandwidth memory path 918, and the graphics / video card 912 can be coupled to the MCH 916 via an Accelerated Graphics Port ("AGP") interconnect 914.

[0087] In at least one embodiment, the computer system 900 may use a system I / O 922, which is a proprietary hub interface bus to couple the MCH 916 to an I / O controller hub ("ICH") 930. In at least one embodiment, the ICH 930 may provide direct connection to certain I / O devices through 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 used to connect peripheral devices to the memory 920, the chipset, and the processor 902. Examples may include, but are not limited to, an audio controller 929, a firmware hub ("Flash BIOS") 928, a wireless transceiver 926, a data store 924, a traditional I / O controller 923 including a user input and keyboard interface 925, a serial expansion port 927 (e.g., a universal serial bus (USB) port), and a network controller 934. The data store 924 may include a hard drive, a floppy drive, a CD-ROM device, a flash memory device, or other mass storage device.

[0088] In at least one embodiment, Fig. 9 A system comprising interconnected hardware devices or "chips" is shown, while in other embodiments, Fig. 9An exemplary system on chip (SoC) may be shown. In at least one embodiment, the devices 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 computer system 900 are interconnected using a compute express link (CXL) interconnect.

[0089] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations related to one or more embodiments. Fig. 7A and / or Figure 7B Provide details about the reasoning and / or training logic 715. In at least one embodiment, the reasoning and / or training logic 715 may be Fig. 9 for use in a system for performing inference or prediction operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0090] Such components can be used for object creation and modification.

[0091] Fig.10 1 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 notebook computer, a tower server, a rack server, a blade server, a laptop computer, a desktop computer, a tablet computer, a mobile device, a phone, an embedded computer, or any other suitable electronic device.

[0092] In at least one embodiment, the electronic device 1000 may include, but is not limited to, a processor 1010 communicatively coupled to any suitable number or kind of components, peripherals, modules, or devices. In at least one embodiment, the processor 1010 is coupled using a bus or interface, such as an Ic 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 attachment ("SATA") bus, a universal serial bus ("USB") (versions 1, 2, 3), or a universal asynchronous receiver / transmitter ("UART") bus. In at least one embodiment, Fig.10 A system is shown that includes interconnected hardware devices or "chips", while in other embodiments, Fig.10 An exemplary system on chip (SoC) may be shown. In at least one embodiment, Fig.10 The devices shown in can be interconnected with a proprietary interconnect, a standardized interconnect (e.g., PCIe), or some combination thereof. In at least one embodiment, Fig.10 One or more components of the system are interconnected using Compute Express Link (CXL) interconnect lines.

[0093] In at least one embodiment, Fig.10 It may include a display 1024, a touch screen 1025, a touch pad 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 memory (“BIOS, FW Flash”) 1022, a DSP 1060, a drive 1020 (e.g., a solid state disk (“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 with, for example, the LPDDR3 standard. These components may each be implemented in any suitable manner.

[0094] In at least one embodiment, other components may be communicatively coupled to the processor 1010 through the components described above. In at least one embodiment, the accelerometer 1041, ambient light sensor (“ALS”) 1042, compass 1043, and gyroscope 1044 may be communicatively coupled to the sensor hub 1040. In at least one embodiment, the thermal sensor 1039, fan 1037, keyboard 1036, and touchpad 1030 may be communicatively coupled to the EC 1035. In at least one embodiment, the speaker 1063, earphone 1064, and microphone (“mic”) 1065 may be communicatively coupled to the audio unit (“audio codec and class D amplifier”) 1062, which in turn may be communicatively coupled to the DSP 1060. In at least one embodiment, the audio unit 1062 may include, for example, but not limited to, an audio encoder / decoder (“codec”) and a class D amplifier. In at least one embodiment, the SIM card (“SIM”) 1057 may be communicatively coupled to the WWAN unit 1056. In at least one embodiment, components such as the WLAN unit 1050 and the Bluetooth unit 1052 and the WWAN unit 1056 may be implemented as a next generation form factor (NGFF).

[0095] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. Fig. 7A and / or Figure 7B Provide details about the reasoning and / or training logic 715. In at least one embodiment, the reasoning and / or training logic 715 may be Fig.10Systems for performing inference or prediction operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0096] Such components can be used for object creation and modification.

[0097] Fig.11 1100 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 can be a single-processor desktop system, a multi-processor workstation system, or a server system with 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-chip (SoC) integrated circuit for use in a mobile, handheld, or embedded device.

[0098] In at least one embodiment, the system 1100 may include or be incorporated into a server-based gaming platform, including a gaming console, a mobile gaming console, a handheld gaming console, or an online gaming console for gaming and media consoles. In at least one embodiment, the system 1100 is a mobile phone, a smart phone, a tablet computing device, or a mobile Internet device. In at least one embodiment, the processing system 1100 may also include a wearable device coupled to or integrated in a wearable device, such as a smart watch wearable device, a smart glasses device, an augmented reality device, or a virtual reality device. In at least one embodiment, the 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.

[0099] In at least one embodiment, one or more processors 1102 each include one or more processor cores 1107 to process instructions that, when executed, perform operations for 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 group 1109. In at least one embodiment, the instruction group 1109 can facilitate complex instruction set computing (CISC), reduced instruction set computing (RISC), or calculate by very long instruction words (VLIW). In at least one embodiment, one or more processor cores 1107 can each process different instruction groups 1109, which can include instructions that help emulate other instruction groups. In at least one embodiment, one or more processor cores 1107 can also include other processing devices, such as digital signal processors (DSPs).

[0100] In at least one embodiment, one or more processors 1102 include cache memory 1104. In at least one embodiment, one or more processors 1102 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory is shared between various components of one or more processors 1102. In at least one embodiment, one or more processors 1102 also use an external cache (e.g., a level 3 (L3) cache or a last level cache (LLC)) (not shown), which may be shared between one or more processor cores 1107 using known cache coherence techniques. In at least one embodiment, one or more processors 1102 additionally include a register file 1106, and the processor 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, the register file 1106 may include general registers or other registers.

[0101] 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 one or more processors 1102 and other components in the system 1100. In at least one embodiment, one or more interface buses 1110 may be a processor bus, such as a version of a direct media interface (DMI) bus, in one embodiment. In at least one embodiment, one or more interface buses 1110 are not limited to DMI buses, 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 connections to I / O devices through a local I / O bus.

[0102] In at least one embodiment, the 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 have appropriate performance to be used as a processor memory. In at least one embodiment, the memory device 1120 may be used as a system memory of the processing system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute applications or processes. In at least one embodiment, the memory controller 1116 is also coupled to an optional external graphics processor 1112, which may communicate with one or more graphics processors 1108 in the one or more processors 1102 to perform graphics and media operations. In at least one embodiment, a display device 1111 may be connected to the processor 1102. In at least one embodiment, the display device 1111 may include one or more of the internal display devices, such as in a mobile electronic device or laptop device or an external display device connected via a display interface (e.g., DisplayPort, etc.). In at least one embodiment, the display device 1111 may include a head mounted display (HMD), such as a stereoscopic display device used in virtual reality (VR) applications or augmented reality (AR) applications.

[0103] In at least one embodiment, the platform controller hub 1130 enables peripheral devices to be connected to the memory device 1120 and one or more processors 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripherals 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, a data storage device 1124 (e.g., a hard drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 can 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 can include a touch screen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 can be a Wi-Fi transceiver, a Bluetooth transceiver, or a mobile network transceiver, such as a 3G, 4G, or long-term evolution (LTE) transceiver. In at least one embodiment, the firmware interface 1128 enables communication with the system firmware and can be, for example, a unified extensible firmware interface (UEFI). In at least one embodiment, the network controller 1134 can enable a network connection to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to one or more interface buses 1110. In at least one embodiment, the audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, the processing system 1100 includes an optional legacy I / O controller 1140 for coupling legacy (e.g., Personal System 2 (PS / 2)) devices to the system 1100. In at least one embodiment, the platform controller hub 1130 can also be connected to one or more universal serial bus (USB) controllers 1142, which connect input devices such as a keyboard and mouse 1143 combination, a camera 1144, or other USB input devices.

[0104] In at least one embodiment, instances of 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, platform controller hub 1130 and / or 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 a peripheral controller hub in a system chipset that communicates with processor 1102.

[0105] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. Fig. 7A and / or Figure 7B Detail is provided regarding the inference and / or training logic 715. 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 that are embodied in the graphics processor. In addition, in at least one embodiment, the inference and / or training operations described herein may use the ALUs other than the ALUs. Fig. 7A and / or Figure 7B 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) that configure the ALU of the graphics processor to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0106] Such components can be used for object creation and modification.

[0107] Fig.12 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 in accordance with at least one embodiment. In at least one embodiment, the processor 1200 may include additional cores, up to and including the additional core 1202N represented by the dashed box. In at least one embodiment, each of the one or more processor cores 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core may also have access to one or more shared cache units 1206.

[0108] In at least one embodiment, one or more internal cache units 1204A-1204N and one or more shared cache units 1206 represent a cache memory hierarchy within the processor 1200. In at least one embodiment, the one or more 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 mid-level cache, such as level 2 (L2), level 3 (L3), level 4 (L4), or other levels of cache, where the highest level of cache before external memory is classified as LLC. In at least one embodiment, cache coherency logic maintains coherency between the various cache units 1206 and 1204A-1204N.

[0109] In at least one embodiment, the processor 1200 may also include a set of one or more bus controller units 1216 and a system agent core 1210. In at least one embodiment, the 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).

[0110] In at least one embodiment, one or more processor cores 1202A-1202N include support for multiple threads simultaneously. In at least one embodiment, system agent core 1210 includes components for coordinating and operating one or more processor cores 1202A-1202N during multithreaded processing. In at least one embodiment, system agent core 1210 may additionally include a power control unit (PCU) that includes logic and components for regulating one or more power states of one or more processor cores 1202A-1202N and graphics processor 1208.

[0111] In at least one embodiment, the processor 1200 also includes a graphics processor 1208 for performing graphics processing operations. In at least one embodiment, the graphics processor 1208 is coupled to one or more shared cache units 1206 and a system agent core 1210 including one or more integrated memory controllers 1214. In at least one embodiment, the system agent core 1210 also includes a display controller 1211 for driving the graphics processor output to one or more coupled displays. In at least one embodiment, the display controller 1211 may also be a separate module coupled to the graphics processor 1208 via at least one interconnect, or may be integrated within the graphics processor 1208.

[0112] In at least one embodiment, a ring-based interconnect unit 1212 is used to couple the internal components of the processor 1200. In at least one embodiment, alternative interconnect units may be used, such as point-to-point interconnects, switched interconnects, or other technologies. In at least one embodiment, the graphics processor 1208 is coupled to the ring-based interconnect unit 1212 via an I / O link 1213.

[0113] 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 modules 1218 (e.g., eDRAM modules). In at least one embodiment, each of one or more processor cores 1202A-1202N and graphics processor 1208 uses embedded memory module 1218 as a shared last level cache.

[0114] In at least one embodiment, one or more processor cores 1202A-1202N are homogeneous cores that execute a common instruction set architecture. In at least one embodiment, one or more processor cores 1202A-1202N are heterogeneous in terms of instruction set architecture (ISA), wherein one or more processor cores 1202A-1202N execute a common instruction set, while one or more other cores in one or more processor cores 1202A-1202N execute a subset or a different instruction set of the common instruction set. In at least one embodiment, one or more processor cores 1202A-1202N are heterogeneous in terms of microarchitecture, wherein one or more cores with relatively high power consumption are coupled with one or more power cores with lower power consumption. In at least one embodiment, processor 1200 can be implemented on one or more chips or implemented as a SoC integrated circuit.

[0115] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. Fig. 7A and / or Figure 7B Detail is provided regarding the inference and / or training logic 715. 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 Fig.12 In addition, in at least one embodiment, the inference and / or training operations described herein may use the inference and / or training operations described herein. Fig. 7A and / or Figure 7B 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) that configure the ALU of the graphics processor 1200 to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0116] Such components can be used for object creation and modification.

[0117] Virtualized computing platform

[0118] Fig.13 is an example data flow diagram of a process 1300 for generating and deploying an image processing and inference pipeline according to at least one embodiment. In at least one embodiment, the process 1300 can be deployed for use with imaging devices, processing devices, and / or other device types at one or more facilities 1302. The process 1300 can be executed within a training system 1304 and / or a deployment system 1306. In at least one embodiment, the training system 1304 can be used to perform training, deployment, and implementation of machine learning models (e.g., neural networks, object detection algorithms, computer vision algorithms, etc.) for use with the deployment system 1306. In at least one embodiment, the deployment system 1306 can be configured to offload processing and computing resources in a distributed computing environment to reduce infrastructure requirements of the facility 1302. In at least one embodiment, one or more applications in the pipeline can use or call services (e.g., reasoning, visualization, computation, AI, etc.) of the deployment system 1306 during application execution.

[0119] In at least one embodiment, some applications used in the high-level processing and reasoning pipeline may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, the machine learning model may be trained at the facility 1302 using data 1308 (e.g., imaging data) generated at the facility 1302 (and stored on one or more picture archiving and communication system (PACS) servers at the facility 1302), the machine learning model may be trained using imaging or sequencing data 1308 from another one or more facilities, or a combination thereof. In at least one embodiment, the training system 1304 may be used to provide applications, services, and / or other resources to generate a working, deployable machine learning model for the deployment system 1306.

[0120] In at least one embodiment, the model registry 1324 can be backed by an object store, which can support versioning and object metadata. In at least one embodiment, the object store can be accessed from within the cloud platform through, for example, a cloud storage compatible application programming interface (API). In at least one embodiment, the machine learning models within the model registry 1324 can be uploaded, listed, modified, or deleted by developers or partners of the system interacting with the API. In at least one embodiment, the API can provide access to methods that allow users with appropriate credentials to associate a model with an application so that the model can be executed as part of the execution of a containerized instantiation of the application.

[0121] In at least one embodiment, the training system 1304 ( Fig.13) may include situations where the facility 1302 is training their own machine learning model, or has an existing machine learning model that needs to be optimized or updated. In at least one embodiment, imaging data 1308 generated by an imaging device, a sequencing device, and / or other type of device may be received. In at least one embodiment, once the imaging data 1308 is received, the AI-assisted annotation 1310 may be used to help generate annotations corresponding to the imaging data 1308 to be used as ground truth data for the machine learning model. In at least one embodiment, the AI-assisted annotation 1310 may include one or more machine learning models (e.g., a convolutional neural network (CNN)) that may be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, the AI-assisted annotation 1310 may then be used directly, or may be adjusted or fine-tuned using an annotation tool to generate ground truth data. In at least one embodiment, the AI-assisted annotation 1310, the labeled data 1312, or a combination thereof may be used as ground truth data for training a machine learning model. In at least one embodiment, the trained machine learning models may be referred to as one or more output models 1316 and may be used by the deployment system 1306 as described herein.

[0122] In at least one embodiment, the training pipeline may include a scenario where the facility 1302 requires a machine learning model for performing one or more processing tasks for one or more applications in the deployment system 1306, but the facility 1302 may not currently have such a machine learning model (or may not have a model that is optimized, efficient, or effective for this purpose). In at least one embodiment, an existing machine learning model may be selected from the model registry 1324. In at least one embodiment, the model registry 1324 may include machine learning models that are trained to perform a variety of different reasoning tasks on imaging data. In at least one embodiment, the machine learning models in the model registry 1324 may be trained on imaging data from a different facility (e.g., a facility located far away) rather than the facility 1302. In at least one embodiment, the machine learning model may have been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when training is performed on imaging data from a specific location, the 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. In at least one embodiment, once a model is trained or partially trained at one location, the machine learning model can be added to the 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 the model registry 1324. In at least one embodiment, the machine learning model can then be selected from the model registry 1324 (and referred to as the output model 1316) and can be deployed in the deployment system 1306 to perform one or more processing tasks for one or more applications of the deployment system.

[0123] In at least one embodiment, the scenario may include a facility 1302 that requires a machine learning model for performing one or more processing tasks for one or more applications in the deployment system 1306, but the 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 the model registry 1324 may not be fine-tuned or optimized for the imaging data 1308 generated at the facility 1302 due to population differences, robustness of the training data used to train the machine learning model, diversity of training data anomalies, and / or other issues with the training data. In at least one embodiment, AI-assisted annotations 1310 may be used to help generate annotations corresponding to the imaging data 1308 for use as ground truth data for training or updating the machine learning model. In at least one embodiment, the labeled data 1312 may be used as ground truth 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 data 1312, or a combination thereof) can be used as ground truth data to retrain or update a machine learning model. In at least one embodiment, the trained machine learning model can be referred to as an output model 1316 and can be used by the deployment system 1306, as described herein.

[0124] In at least one embodiment, the deployment system 1306 may include software 1318, services 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, the deployment system 1306 may include a software "stack" such that the software 1318 may be built on top of the services 1320 and may use the services 1320 to perform some or all of the processing tasks, and the services 1320 and software 1318 may be built on top of the hardware 1322 and use the hardware 1322 to perform the processing, storage, and / or other computing tasks of the deployment system. In at least one embodiment, the software 1318 may include any number of different containers, each of which may perform an instantiation of an application. In at least one embodiment, each application may perform one or more processing tasks (e.g., reasoning, object detection, feature detection, segmentation, image enhancement, calibration, etc.) in a high-level processing and reasoning pipeline. In at least one embodiment, in addition to receiving and configuring imaging data for use by each container and / or containers used by facility 1302 after processing through the pipeline, a high-level processing and reasoning pipeline can also be defined based on the selection of different containers desired or required to process imaging data 1308 (e.g., to convert the output back into a usable data type. In at least one embodiment, the combination of containers within software 1318 (e.g., which constitute a pipeline) can be referred to as a virtual instrument (as described in more detail herein), and the virtual instrument can utilize services 1320 and hardware 1322 to perform some or all of the processing tasks of an application instantiated in a container.

[0125] In at least one embodiment, the data processing pipeline can 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 the deployment system 1306). In at least one embodiment, the input data can 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 can be pre-processed as part of the data processing pipeline to prepare the data for processing by one or more applications. In at least one embodiment, post-processing can 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 prepare the output data for transmission and / or use by the user (e.g., as a response to the inference request). In at least one embodiment, the inference task can be performed by one or more machine learning models, such as trained or deployed neural networks, which can include one or more output models 1316 of the training system 1304.

[0126] In at least one embodiment, tasks of a data processing pipeline may 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 may be published to a private (e.g., limited access) area of ​​a container registry (described in more detail herein), and trained or deployed models may be stored in the model registry 1324 and associated with one or more applications. In at least one embodiment, an image of an application (e.g., a container image) may be available in a container registry, and once a user selects an image from a container registry for deployment in a pipeline, the image may be used to generate an instantiated container for the application for use by the user's system.

[0127] In at least one embodiment, a developer (e.g., a software developer, a clinician, a physician, etc.) can develop, publish, and store applications (e.g., as containers) for performing image processing and / or reasoning on provided data. In at least one embodiment, the development, publishing, and / or storage can be performed using a software development kit (SDK) associated with the system (e.g., to ensure that the developed applications and / or containers conform to or are compatible with the system). In at least one embodiment, the developed applications can be tested locally (e.g., at a first facility, on data from the first facility) using the SDK, which is installed as part of the system (e.g., Fig.12 Processor 1200 in the process 1300) may support at least some services 1320. In at least one embodiment, because a DICOM object may contain from one to hundreds of images or other data types, and because the data varies, the developer may be responsible for managing (e.g., setting up constructs for building pre-processing into the application, etc.) the extraction and preparation of the incoming data. In at least one embodiment, once validated by process 1300 (e.g., for accuracy), the application is made available in the container registry for selection and / or implementation by the user to perform one or more processing tasks on the data at the user's facility (e.g., a second facility).

[0128] In at least one embodiment, the developer can then share the application or container over a network for use by a system (e.g., Fig.131300). In at least one embodiment, the completed and validated application or container can be stored in the container registry, and the associated machine learning model can be stored in the model registry 1324. In at least one embodiment, the requesting entity (which provides the reasoning or image processing request) can browse the container registry and / or the model registry 1324 to obtain applications, containers, data sets, machine learning models, etc., select the desired combination of elements to be included in the data processing pipeline, and submit the image processing request. In at least one embodiment, the request may include the input data necessary to execute the request (and in some examples, patient-related data), and / or may include a selection of applications and / or machine learning models to be executed when processing the request. In at least one embodiment, the request can then be passed to one or more components (e.g., a cloud) of the deployment system 1306 to perform processing of the data processing pipeline. In at least one embodiment, the processing performed by the deployment system 1306 may include referencing elements (e.g., applications, containers, models, etc.) selected from the container registry and / or the model registry 1324. In at least one embodiment, once the results are generated by the pipeline, the results may be returned to the user for reference (eg, for viewing in a viewing application suite executing locally, on a local workstation or terminal).

[0129] In at least one embodiment, to assist in processing or executing applications or containers in the pipeline, services 1320 may be utilized. In at least one embodiment, services 1320 may include computing services, artificial intelligence (AI) services, visualization services, and / or other service types. In at least one embodiment, services 1320 may provide functionality common to one or more applications in software 1318, and thus may abstract functionality into services that may be called or utilized by applications. In at least one embodiment, the functionality provided by services 1320 may run dynamically and more efficiently, while also allowing applications to process data in parallel (e.g., using Fig.12In at least one embodiment, rather than requiring that each application that shares the same functionality provided by the service 1320 must have a corresponding instance of the service 1320, 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 that can provide machine learning model training and / or retraining capabilities. In at least one embodiment, a data enhancement service may be further included that can provide GPU-accelerated data (e.g., DICOM, RIS, CIS, REST-compliant, RPC, raw, etc.) extraction, resizing, scaling, and / or other enhancements. In at least one embodiment, a visualization service may be used that 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 that provides beamforming, segmentation, reasoning, imaging, and / or support for other applications within the pipeline of the virtual instrument.

[0130] In at least one embodiment, where the service 1320 includes an AI service (e.g., an inference service), as part of the execution of an application, one or more machine learning models can be executed by calling (e.g., as an API call) an inference service (e.g., an inference server) to execute one or more machine learning models or processing thereof. In at least one embodiment, where another application includes one or more machine learning models for a segmentation task, the application can call the inference service to execute the machine learning model for performing one or more processing operations associated with the segmentation task. In at least one embodiment, the software 1318 implementing the high-level processing and inference pipeline, which includes a segmentation application and anomaly detection application, can be pipelined because each application can call the same inference service to perform one or more inference tasks.

[0131] In at least one embodiment, the hardware 1322 may include a GPU, a CPU, a graphics card, an AI / deep learning system (e.g., an AI supercomputer such as NVIDIA's DGX), a cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient, purpose-built support for the software 1318 and services 1320 in the deployment system 1306. In at least one embodiment, the use of GPU processing may be implemented to perform local processing (e.g., at the facility 1302) within the AI / deep learning system, in the cloud system, and / or other processing components of the deployment system 1306 to improve the efficiency, accuracy, and effectiveness of image processing and generation. In at least one embodiment, as a non-limiting example, with respect to deep learning, machine learning, and / or high-performance computing, the software 1318 and / or services 1320 may be optimized for GPU processing. In at least one embodiment, at least some of the computing environments of the deployment system 1306 and / or training system 1304 may be executed in a data center, one or more supercomputers, or high-performance computer systems with GPU-optimized software (e.g., a combination of hardware and software of an NVIDIA DGX system). In at least one embodiment, as described herein, hardware 1322 may include any number of GPUs that may be called 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 computing tasks. In at least one embodiment, an AI / deep learning supercomputer and / or GPU optimized software (e.g., as provided on NVIDIA's DGX system) may be used as a hardware abstraction and scaling platform to execute a cloud platform (e.g., NVIDIA's NGC). In at least one embodiment, the cloud platform may integrate an application container cluster system or coordination system (e.g., KUBERNETES) on multiple GPUs to achieve seamless scaling and load balancing.

[0132] Fig.14 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, the system 1400 can be used to implement Fig.13 The process 1300 and / or other processes of the system 1400 may include a high-level processing and reasoning pipeline. In at least one embodiment, the system 1400 may include a training system 1304 and a deployment system 1306. In at least one embodiment, the training system 1304 and the deployment system 1306 may be implemented using software 1318, services 1320, and / or hardware 1322, as described herein.

[0133] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) can be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 can be implemented locally (with respect to a healthcare service facility) or as a combination of cloud computing resources and local computing resources. In at least one embodiment, access to APIs in cloud 1426 can be restricted to authorized users by establishing security measures or protocols. In at least one embodiment, the security protocol can include a network token, which can be signed by an authentication (e.g., AuthN, AuthZ, Gluecon, etc.) service and can carry appropriate authorization. In at least one embodiment, the API of the virtual instrument (described herein) or other instances of system 1400 can be restricted to a set of public IPs that have been audited or authorized for interaction.

[0134] In at least one embodiment, the various components of system 1400 can 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, communications between facilities and components of system 1400 (e.g., for sending inference requests, for receiving results of inference requests, etc.) can be transmitted via one or more data buses, wireless data protocols (Wi-Fi), wired data protocols (e.g., Ethernet), etc.

[0135] In at least one embodiment, similar to the present disclosure regarding Fig.13 As described, the training system 1304 can execute one or more training pipelines 1404. In at least one embodiment, where the deployment system 1306 will use one or more machine learning models in one or more deployment pipelines 1410, the one or more training pipelines 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 the one or more training pipelines 1404, an output model 1316 can be generated. In at least one embodiment, the one or more training pipelines 1404 can include any number of processing steps, such as, but not limited to, conversion or adaptation of imaging data (or other input data). In at least one embodiment, different one or more training pipelines 1404 can be used for different machine learning models used by the deployment system 1306. In at least one embodiment, similar to the description of Fig.13 The one or more training pipelines 1404 of the first example described may be used for a first machine learning model, similar to the one described with respect to Fig.13The one or more training pipelines 1404 of the second example described may be used for a second machine learning model, similar to the one or more training pipelines 1404 of the second example described. Fig.13 The one or more training pipelines 1404 of the third example described may be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 may 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 been trained and are ready for deployment, so the training system 1304 may not perform any processing on the machine learning model, and one or more machine learning models may be implemented by the deployment system 1306.

[0136] In at least one embodiment, the output model 1316 and / or the pre-trained model 1406 may include any type of machine learning model, depending on the implementation or embodiment. In at least one embodiment and without limitation, the machine learning model used by the system 1400 may include using linear regression, logistic regression, decision tree, support vector machine (SVM), naive Bayes, k-nearest neighbor (Knn), k-means clustering, random forest, dimensionality reduction algorithm, gradient boosting algorithm, neural network (e.g., autoencoder, convolution, recursion, perceptron, long / short term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid state machine, etc.), and / or other types of machine learning models.

[0137] In at least one embodiment, one or more training pipelines 1404 may include AI-assisted annotation, as described herein with respect to at least Fig.14In more detail. In at least one embodiment, the labeled clinical data 1312 (e.g., traditional annotations) can be generated by any number of techniques. In at least one embodiment, in some examples, labels or other annotations can be generated in a drawing program (e.g., an annotation program), a computer-aided design (CAD) program, a labeling program, another type of application suitable for generating ground-truth annotations or labels, and / or can be hand-drawn. In at least one embodiment, the ground-truth data can be synthetically generated (e.g., generated from a computer model or rendering), truly generated (e.g., designed and generated from real-world data), automatically generated by a machine (e.g., extracting features from the data using feature analysis and learning, and then generating labels), manually annotated (e.g., a labeler or annotation expert, defining the location of the label), and / or a combination thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data types used by machine learning models), there can be corresponding ground-truth data generated by the training system 1304. In at least one embodiment, AI-assisted annotations can be performed as part of one or more deployment pipelines 1410; supplementing or replacing AI-assisted annotations included in one or more training pipelines 1404. In at least one embodiment, the system 1400 may include a multi-layer platform that may include a software layer (e.g., software 1318) of a diagnostic application (or other application type) that may perform one or more medical imaging and diagnostic functions. In at least one embodiment, the system 1400 may be communicatively coupled (e.g., via an encrypted link) to a PACS server network of one or more facilities. In at least one embodiment, the system 1400 may be configured to access and reference data from a PACS server to perform operations such as training a machine learning model, deploying a machine learning model, image processing, reasoning, and / or other operations.

[0138] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or authenticated API through which an application or container may be invoked (e.g., called) from an external environment (e.g., facility 1302). In at least one embodiment, the application may then call or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with the respective application, and the software 1318 and / or services 1320 may utilize hardware 1322 to perform processing tasks in an effective and efficient manner. In at least one embodiment, a pair of DICOM adapters 1402A, 1402B may be used for communications sent to or received by the training system 1304 and the deployment system 1306.

[0139] In at least one embodiment, the deployment system 1306 may execute one or more deployment pipelines 1410. In at least one embodiment, the one or more deployment pipelines 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 annotations, generated by imaging devices, sequencing devices, genomics devices, etc., as described above. In at least one embodiment, as described herein, one or more deployment pipelines 1410 for individual devices may be referred to as virtual instruments for the device (e.g., virtual ultrasound instruments, virtual CT scanning instruments, virtual sequencing instruments, etc.). In at least one embodiment, there may be more than one deployment pipeline 1410 for a single device, depending on the information desired from the data generated by the device. In at least one embodiment, in the case where an abnormality is desired to be detected from an MRI machine, there may be one or more first deployment pipelines 1410, and in the case where image enhancement is desired from the output of the MRI machine, there may be one or more second deployment pipelines 1410.

[0140] In at least one embodiment, the image generation application may include a processing task that includes the use of a machine learning model. 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 an application that performs a processing task. In at least one embodiment, the application may be selectable and customizable, and by defining the construction of the application, the deployment and implementation of the application for a particular user is presented as a more seamless user experience. In at least one embodiment, by leveraging other features of the system 1400 (e.g., services 1320 and hardware 1322), one or more deployment pipelines 1410 may be more user-friendly, provide easier integration, and produce more accurate, efficient, and timely results.

[0141] 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 may be used to select applications to be included in deployment pipeline 1410, to arrange applications, to modify or change applications or their parameters or configuration, to use and interact with deployment pipeline 1410 during setup and / or deployment, and / or to otherwise interact with deployment system 1306. In at least one embodiment, although not shown with respect to training system 1304, UI 1414 (or a different user interface) may be used to select models to use in deployment system 1306, to select models for training or retraining in training system 1304, and / or to otherwise interact with training system 1304.

[0142] In at least one embodiment, in addition to the application coordination system 1428, a pipeline manager 1412 may be used to manage the interaction between the application or container of the deployment pipeline 1410 and the service 1320 and / or the hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate the interaction 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 the software 1318, this is not intended to be limiting, and in some examples, the pipeline manager 1412 may be included in the 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 a logical unit 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 be executed in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0143] In at least one embodiment, each application and / or container (or its image) can be developed, modified, and deployed separately (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), which can allow for focus and attention 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 assist in communication and collaboration between different containers or applications. In at least one embodiment, as long as the expected inputs and / or outputs of each container or application are known to the system (e.g., based on the construction of the application or container), the application coordination system 1428 and / or the pipeline manager 1412 can facilitate communication and sharing of resources between and among each application or container. 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 among the various applications or containers. In at least one embodiment, the scheduler can be used to track resource requirements of applications or containers, current or planned use of those resources, and resource availability. Thus, in at least one embodiment, the scheduler can allocate resources to different applications and allocate resources between and among applications, taking into account the needs and availability of the system. 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.

[0144] In at least one embodiment, the services 1320 utilized and shared by the applications or containers in the deployment system 1306 may include computing services 1416, AI services 1418, visualization services 1420, and / or other service types. In at least one embodiment, an application may call (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 services 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 a parallel computing platform 1430) to process data substantially simultaneously by one or more applications and / or one or more tasks of a single application. In at least one embodiment, a parallel computing platform 1430 (e.g., NVIDIA's CUDA) may implement general computing on a GPU (GPGPU) (e.g., GPU / graphics 1422). In at least one embodiment, the software layer of the parallel computing platform 1430 may provide access to a virtual instruction set and parallel computing elements of a GPU 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 among multiple containers, and / or between and among 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 a container to enable the same data (e.g., where multiple different stages of an application or multiple applications are processing the same information) to be used for a shared memory segment from the parallel computing platform 1430. In at least one embodiment, instead of copying data and moving the data to different locations in memory (e.g., read / write operations), the same data in the same location of the memory may be used for any number of processing tasks (e.g., at the same time, at different times, etc.). In at least one embodiment, since the data as a result of processing is used to generate new data, this information of the new location of the data may be stored and shared between various applications. 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 to understand the payload in the container.

[0145] In at least one embodiment, the AI ​​service 1418 may be utilized to perform a reasoning service for executing a machine learning model associated with an application (e.g., a task is to execute one or more processing tasks of an application). In at least one embodiment, the AI ​​service 1418 may utilize the 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 reasoning tasks. In at least one embodiment, the application of the deployment pipeline 1410 may use one or more output models 1316 of the self-training system 1304 and / or other models of the application to perform reasoning on the imaging data. In at least one embodiment, two or more examples of reasoning using the application coordination system 1428 (e.g., a scheduler) may be available. In at least one embodiment, the first category may include a high priority / low latency path that can achieve a higher service level agreement, such as for performing reasoning on an urgent request in an emergency, or for a radiologist during a diagnostic process. In at least one embodiment, the second category may include a standard priority path that may be used for requests that may not be urgent or where analysis can be performed at a later time. In at least one embodiment, application coordination system 1428 may allocate resources (e.g., services 1320 and / or hardware 1322) for different reasoning tasks of one or more AI services 1418 based on priority paths.

[0146] In at least one embodiment, the shared memory may be mounted to one or more AI services 1418 in the system 1400. In at least one embodiment, the 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 the 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, in order to process the request, the request may be entered into a database, and if it is not already in the cache, the machine learning model may be located from the model registry 1324, a verification step may ensure that the appropriate machine learning model is loaded into the cache (e.g., shared storage), and / or a copy of the model may be saved to the cache. In at least one embodiment, if the application is not yet running or there are not enough instances of the application, a scheduler (e.g., a scheduler of the pipeline manager 1412) may be used to start the application referenced in the request. In at least one embodiment, if the inference server has not yet been started to execute the model, the 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 beneficial. In at least one embodiment, the inference servers can be statically loaded into the corresponding distributed servers.

[0147] In at least one embodiment, inference can be performed using an inference server running in a container. In at least one embodiment, an instance of an inference server can be associated with a model (and optionally with multiple versions of a model). In at least one embodiment, if an instance of an inference server does not exist when a request is received to perform inference on a model, a new instance can be loaded. In at least one embodiment, when the inference server is started, the model can be passed to the inference server so that the same container can be used to serve different models as long as the inference server is running as a different instance.

[0148] In at least one embodiment, during application execution, a request for reasoning for a given application may be received, and a container (e.g., an instance of a hosting reasoning server) may be loaded (if not already loaded), and a launcher may be called. In at least one embodiment, preprocessing logic in the container may load, decode, and / or perform any additional preprocessing on the incoming data (e.g., using a CPU and / or GPU). In at least one embodiment, once the data is ready for reasoning, the container may perform reasoning on the data as needed. In at least one embodiment, this may include a single reasoning call for one image (e.g., a hand X-ray), or may require reasoning for hundreds of images (e.g., a chest CT). In at least one embodiment, the application may 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 may 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 may be measured from a requesting mechanism or entity and may include collaborative network traversal time as well as execution time of an inference service.

[0149] In at least one embodiment, the transmission of requests between the service 1320 and the reasoning application can be hidden behind a software development kit (SDK), and robust transmission can be provided through queues. In at least one embodiment, requests will be placed in queues through an API for individual application / tenant ID combinations, and the SDK will pull requests from the queue and provide the request to the application. In at least one embodiment, the name of the queue can be provided in the environment from which the SDK will pick up the queue. In at least one embodiment, asynchronous communication through queues may be useful because it can allow any instance of the application to pick up work when it is available. Results can be transmitted back through the queue to ensure that no data is lost. In at least one embodiment, the queue can also provide the ability to split the work, because the highest priority work can enter the queue connected to most instances of the application, and the lowest priority work can enter the queue connected to a single instance, which processes the tasks in the order received. In at least one embodiment, the application can run on a GPU-accelerated instance generated in the cloud 1426, and the reasoning service can perform reasoning on the GPU.

[0150] In at least one embodiment, one or more visualization services 1420 may be utilized to generate visualizations for viewing application and / or deployment pipeline 1410 outputs. In at least one embodiment, one or more visualization services 1420 may utilize GPU / graphics 1422 to generate visualizations. In at least one embodiment, one or more visualization services 1420 may implement rendering effects such as ray tracing to generate higher quality visualizations. In at least one embodiment, visualizations may include, but are not limited to, 2D image rendering, 3D volume rendering, 3D volume reconstruction, 2D tomographic slices, virtual reality displays, augmented reality displays, and the like. In at least one embodiment, a virtualized environment may be used to generate a virtual interactive display or environment (e.g., a virtual environment) for system users (e.g., doctors, nurses, radiologists, etc.) to interact with. In at least one embodiment, one or more visualization services 1420 may include an internal visualizer, movie, and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0151] In at least one embodiment, hardware 1322 may include GPU / graphics 1422, AI system 1424, cloud 1426, and / or any other hardware for executing 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 functionality of one or more computing services 1416, one or more AI services 1418, one or more visualization services 1420, other services, and / or software 1318. For example, for one or more AI services 1418, GPU / graphics 1422 may be used to perform pre-processing on imaging data (or other data types used by machine learning models), post-processing on the output of machine learning models, and / or perform 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 cloud 1426 (or at least part of a task being deep learning or reasoning) may be executed using one or more AI systems 1424. Likewise, while hardware 1322 is shown as discrete components, 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.

[0152] In at least one embodiment, AI system 1424 may include a purpose-built computing system (e.g., a supercomputer or HPC) configured for reasoning, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, in addition to CPU, RAM, storage, 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 use multiple GPUs / graphics 1422 to perform GPU-optimized tasks. 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.

[0153] In at least one embodiment, cloud 1426 may include a GPU-accelerated infrastructure (e.g., NVIDIA's NGC) that may provide a GPU-optimized platform for executing processing tasks of system 1400. In at least one embodiment, cloud 1426 may include an AI system 1424 for executing 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 an application coordination system 1428 that utilizes multiple GPUs to enable seamless scaling and load balancing between and among applications and services 1320. In at least one embodiment, cloud 1426 may be responsible for executing at least some services 1320 of system 1400, including one or more compute services 1416, one or more AI services 1418, and / or one or more visualization services 1420, as described herein. In at least one embodiment, cloud 1426 can perform large and small batch inference (e.g., executing NVIDIA's TENSORRT), provide accelerated parallel computing APIs and platforms 1430 (e.g., NVIDIA's CUDA), execute application coordination system 1428 (e.g., Kubernetes), provide graphics rendering APIs and platforms (e.g., for ray tracing, 2D graphics, 3D graphics, and / or other rendering techniques to produce higher quality movie effects), and / or can provide other functionality for system 1400.

[0154] Fig.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 may be used. Fig.14The system 1400 of FIG. 1400 performs the process 1500. In at least one embodiment, the process 1500 can utilize services and / or hardware, as described herein. In at least one embodiment, the refined model 1512 generated by the process 1500 can be executed by the deployment system for one or more containerized applications in the deployment pipeline.

[0155] In at least one embodiment, model training 1514 may include retraining or updating an initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data (such as customer data set 1506), and / or new ground truth 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 take as long or require as much processing as training the model from scratch. In at least one embodiment, during model training 1514, by resetting or replacing the output or loss layer of the initial model 1504, when generating predictions on the new customer data set 1506, the parameters for the new data set may be updated and re-adjusted based on the loss calculation associated with the accuracy of the output or loss layer.

[0156] 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 in part at one or more facilities other than the facility performing process 1500. In at least one embodiment, in order to protect the privacy and rights of patients, subjects, or customers of 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 cloud and / or other hardware may be used to train the pre-trained model 1506, but confidential, privacy-protected patient data may not be transmitted 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, for example where customer or patient data has been issued privacy issues (e.g., by being relinquished, used for experimental purposes, etc.), or where the customer or patient data is included in a public dataset, customer or patient data from any number of facilities can be used to train pre-trained model 1506 locally and / or externally, such as in a data center or other cloud computing infrastructure.

[0157] In at least one embodiment, when selecting an application to use in a deployment pipeline, a user may also select a machine learning model to use for a particular application. In at least one embodiment, a user may not have a model to use, 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 customer data set 1506 of the user facility (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 deploying the pre-trained model into a deployment pipeline for use with one or more applications.

[0158] In at least one embodiment, a user may select a pre-trained model to update, retrain, and / or fine-tune, and the pre-trained model may be referred to as the initial model 1504 for the training system in process 1500. In at least one embodiment, a customer data set 1506 (e.g., imaging data, genomic data, sequencing data, or other data types generated by equipment at a 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 truth data corresponding to the customer data set 1506 may be generated by the training system 1304. In at least one embodiment, the ground truth data may be generated, at least in part, at the facility by a clinician, scientist, physician, practitioner.

[0159] In at least one embodiment, AI-assisted annotation can be used in some examples to generate ground truth data. In at least one embodiment, AI-assisted annotation (e.g., implemented using an AI-assisted annotation SDK) can utilize a machine learning model (e.g., a neural network) to generate ground truth data for suggestions or predictions for a customer data set. In at least one embodiment, a user can use the annotation tool within a user interface (graphical user interface (GUI)) on a computing device.

[0160] 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, a polygon editing feature can be used to move vertices of a polygon to a more precise or fine-tuned position.

[0161] In at least one embodiment, once the customer dataset 1506 has associated ground truth data, the ground truth data (e.g., from AI-assisted annotations, manual labeling, etc.) can be used during model training to generate a refined model 1512. In at least one embodiment, the customer dataset 1506 can be applied to the initial model 1504 any number of times, and the ground truth 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, the refined model 1512 can be deployed within one or more deployment pipelines at a facility for use in performing one or more processing tasks with respect to medical imaging data.

[0162] In at least one embodiment, the refined model 1512 can be uploaded to the pre-trained models in the model registry for selection by another facility. In at least one embodiment, this process can be completed at any number of facilities, so that the refined model 1512 can be further refined any number of times on new data sets to generate a more general model.

[0163] Fig. 15B is an example illustration of a client-server architecture 1532 for augmenting an annotation tool with a pre-trained annotation model in accordance with 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 annotation tool 1536 in an imaging application may assist a radiologist, for example, in identifying organs and anomalies. In at least one embodiment, the imaging application may include a software tool that, as a non-limiting example, assists a user 1510 in identifying several extreme points on a particular organ of interest in an original image 1534 (e.g., in a 3D MRI or CT scan) and receiving automatic annotation results for all 2D slices of the particular organ. In at least one embodiment, the results may be stored in a data store as training data 1538 and used as, for example, but not limited to, ground truth data for training. In at least one embodiment, when a computing device 1508 sends extreme points for AI-assisted annotation, for example, a deep learning model may receive the data as input and return an inference result for segmenting an organ or anomaly. In at least one embodiment, a pre-instantiated annotation tool (e.g., Fig. 15B The AI-assisted annotation tool 1536 in the annotation assistant server 1540 can be enhanced by making an API call (e.g., API call 1544) to a server (such as an annotation assistant server 1540), which may include a set of pre-trained models 1542 stored in, for example, an annotation model registry. In at least one embodiment, the annotation model registry can store one or more pre-trained models 1542 (e.g., machine learning models, such as deep learning models) that are pre-trained to perform AI-assisted annotation on specific organs or abnormalities. In at least one embodiment, these models can be further updated by using a training pipeline. In at least one embodiment, the pre-installed annotation tools can be improved over time as new annotated data is added.

[0164] Various embodiments may be described by the following terms:

[0165] 1. A computer-implemented method comprising:

[0166] receiving input corresponding to content of a selected portion of a 3D volume corresponding to a first neural radiance field (NeRF) of a scene;

[0167] generating a second NeRF of the selected portion based at least on the input; and

[0168] An output NeRF is generated by mixing the first NeRF and the second NeRF.

[0169] 2. The computer-implemented method of clause 1, further comprising:

[0170] determining a characteristic value for a region of the first NeRF;

[0171] determining an overwrite feature value for the region of the second NeRF; and

[0172] The feature value is replaced by the overwritten feature value in the output NeRF.

[0173] 3. The computer-implemented method of clause 1, wherein the input is a text prompt.

[0174] 4. The computer-implemented method of clause 1, further comprising:

[0175] receiving an interaction with the first NeRF, the interaction corresponding to the selected portion;

[0176] determining a depth of the selected portion based at least on a parameter of the interaction; and

[0177] The selected portion is generated using the depth.

[0178] 5. The computer-implemented method of clause 1, wherein the output NeRF is generated by a diffusion model.

[0179] 6. The computer-implemented method of clause 1, wherein the input is associated with a tool for making a selection.

[0180] 7. The computer-implemented method of clause 1, wherein the selected portion is a two-dimensional selection based on a first camera perspective, the method further comprising:

[0181] generating one or more rays from a virtual camera associated with the first camera perspective;

[0182] identifying one or more cells intersected by the one or more rays; and

[0183] A depth of the one or more cells is determined.

[0184] 8. A computer-implemented method as described in clause 7, wherein the depth is related to the duration of the interaction with the selected portion.

[0185] 9. The computer-implemented method of clause 1, further comprising:

[0186] generating a mask corresponding to the selected portion; and

[0187] The mask is provided to the content generation pipeline.

[0188] 10. The computer-implemented method of clause 1, further comprising:

[0189] Rendering the object in an interactive environment; and

[0190] One or more tools are provided in the interactive environment to identify the selected portion.

[0191] 11. The computer-implemented method of clause 10, wherein the scene and the objects are both objects generated using one or more content generation models.

[0192] 12. A processor, comprising:

[0193] One or more processing units for:

[0194] generating a scene representation as a neural radiance field (NeRF) via one or more diffusion models;

[0195] receiving an input corresponding to a portion of the NeRF;

[0196] generating a modified NeRF for the portion based on the indication, the modified NeRF including one or more content portions different from the NeRF;

[0197] combining the modified NeRF and the NeRF to form an updated NeRF; and

[0198] A visual representation of the updated NeRF is provided.

[0199] 13. The processor of clause 12, wherein combining the modified NeRF with the NeRF corresponds to overwriting one or more feature values ​​of the NeRF with modified feature values ​​of the modified NeRF.

[0200] 14. The processor of clause 12, wherein the portion of the NeRF is a three-dimensional (3D) representation generated from a two-dimensional (2D) input and one or more attributes of the 2D input.

[0201] 15. The processor of clause 12, wherein the indication is at least one of: a textual prompt, an auditory prompt, or a feature associated with the input.

[0202] 16. The processor of clause 12, wherein the processor is included in at least one of:

[0203] A system for performing simulation operations;

[0204] Systems for performing simulated operations to test or validate autonomous machine applications;

[0205] Systems for performing digital twin operations;

[0206] A system for performing light transport simulations;

[0207] Systems for rendering graphical output;

[0208] Systems for performing deep learning operations;

[0209] Systems implemented using edge devices;

[0210] Systems for generating or presenting virtual reality (VR) content;

[0211] Systems for generating or presenting augmented reality (AR) content;

[0212] Systems for generating or presenting mixed reality (MR) content;

[0213] A system comprising one or more virtual machines (VMs);

[0214] Systems for performing conversational AI application operations;

[0215] Systems for performing operations of generative AI applications;

[0216] A system for performing operations using a language model;

[0217] A system for performing one or more generative content operations using a large language model (LLM);

[0218] A system implemented at least in part in a data center;

[0219] A system for performing hardware testing using simulation;

[0220] A system for performing one or more generative content operations using a language model;

[0221] Systems for synthetic data generation;

[0222] A collaborative content creation platform for 3D assets; or

[0223] A system implemented at least in part using cloud computing resources.

[0224] 17. A system comprising:

[0225] One or more processors, including processing circuitry for generating an output representation of a three-dimensional (3D) scene as a combined neural radiance field (NeRF), the combined NeRF comprising an original volume and a modified volume added to the original volume, the modified volume being generated for a selected volume of the original volume based at least on an input corresponding to content of the modified volume.

[0226] 18. The system of clause 17, wherein objects associated with both the original volume and the modified volume are formed using one or more diffusion models.

[0227] 19. The system of clause 17, wherein the modified volume is calculated based on a second input corresponding to a two-dimensional region and a property of the second input.

[0228] 20. The system of clause 17, wherein the system comprises at least one of the following:

[0229] A system for performing simulation operations;

[0230] Systems for performing simulated operations to test or validate autonomous machine applications;

[0231] Systems for performing digital twin operations;

[0232] A system for performing light transport simulations;

[0233] Systems for rendering graphics output;

[0234] Systems for performing deep learning operations;

[0235] Systems implemented using edge devices;

[0236] Systems for generating or presenting virtual reality (VR) content;

[0237] Systems for generating or presenting augmented reality (AR) content;

[0238] Systems for generating or presenting mixed reality (MR) content;

[0239] A system comprising one or more virtual machines (VMs);

[0240] Systems for performing conversational AI application operations;

[0241] Systems for performing operations of generative AI applications;

[0242] A system for performing operations using a language model;

[0243] A system for performing one or more generative content operations using a large language model (LLM);

[0244] A system implemented at least in part in a data center;

[0245] Systems that perform hardware testing using simulation;

[0246] A system for performing one or more generative content operations using a language model;

[0247] Systems for generating synthetic data;

[0248] A collaborative content creation platform for 3D assets; or

[0249] A system implemented at least in part using cloud computing resources.

[0250] Other variations are within the spirit of the present disclosure. Thus, while the disclosed technology is susceptible to various modifications and alternative constructions, certain illustrated embodiments thereof are shown in the drawings and have been described in detail above. However, it should be understood that there is no intention to limit the disclosure to one or more specific forms disclosed, but on the contrary, it is intended to cover all modifications, alternative constructions, and equivalents that fall within the spirit and scope of the present disclosure as defined by the appended claims.

[0251] Unless otherwise noted or clearly contradictory to the context, in the context of describing the disclosed embodiments (particularly in the context of the appended claims), the use of the terms "one" and "an" and "the" and similar references should be interpreted as covering the singular and plural, rather than as definitions of terms. Unless otherwise noted, the terms "include", "have", "include" and "contain" should be interpreted as open terms (meaning "including but not limited to") unless otherwise noted. The term "connected" (which refers to a physical connection when unmodified) should be interpreted as partially or completely included, attached to or connected together, even if there are some interventions. Unless otherwise noted herein, references to numerical ranges herein are intended only to be used as a shorthand method of referring to each individual value falling within the range, respectively, and each individual value is incorporated into the specification as if it were individually described herein. Unless otherwise noted or contradictory to the context, the use of the term "set" (e.g., "item set") or "subset" should be interpreted as a non-empty set including one or more members. Furthermore, unless otherwise indicated or contradicted by context, the term "subset" of a corresponding set does not necessarily mean a proper subset of the corresponding set, but rather a subset and a corresponding set may be equivalent.

[0252] Unless expressly indicated otherwise or clearly contradicted by context, conjunctions such as phrases of the form "at least one of A, B, and C" or "at least one of A, B and C" are understood in context to be generally used to refer to an item, clause, or the like that may be A or B or C, or any non-empty subset of the set A and B and C. For example, in the illustrative example of a set having three members, the conjunction 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}. Thus, such conjunction language is not generally intended to imply that certain embodiments require the presence of at least one of A, at least one of B, and at least one of C. In addition, unless expressly indicated otherwise or contradicted by context, the term "plurality" refers to a plural state (e.g., "plurality of items" means a plurality of items). The number of items in a plurality of items is at least two, but may be more if expressly indicated or indicated by context. Further, the phrase "based on" means "based at least in part on" rather than "based solely on" unless otherwise specified or clear from context.

[0253] Unless otherwise indicated herein or clearly contradictory to 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 and / or combinations thereof) are performed 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 applications) that are jointly executed on one or more processors by hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium in the form of, for example, a computer program that includes a plurality of instructions that can be executed 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., propagated transient electrical or electromagnetic transmissions), but includes non-transitory data storage circuits (e.g., buffers, caches, and queues). In at least one embodiment, code (e.g., executable code or source code) is stored on a set of 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 being executed), causes the computer system to perform the operations described herein. In at least one embodiment, a set of non-transitory computer-readable storage media includes a plurality of non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media in the plurality of non-transitory computer-readable storage media lacks all the code, but the plurality of non-transitory computer-readable storage media stores all the code together. In at least one embodiment, the executable instructions are executed so that different instructions are executed by different processors, for example, a non-transitory computer-readable storage medium stores instructions, and a main central processing unit ("CPU") executes some instructions, while a graphics processing unit ("GPU") executes other instructions. In at least one embodiment, different components of the computer system have separate processors, and different processors execute different subsets of instructions.

[0254] Thus, in at least one embodiment, a computer system is configured to implement one or more services that individually or collectively perform the operations of the processes described herein, and such a computer system is configured with applicable hardware and / or software that enables the implementation of the operations. In addition, a computer system that implements at least one embodiment of the present disclosure is a single device, and in another embodiment is a distributed computer system that includes multiple devices that operate in different ways, so that the distributed computer system performs the operations described herein, and so that a single device does not perform all operations.

[0255] The use of any and all examples or exemplary language (e.g., "such as") provided herein is intended only to better illustrate embodiments of the present disclosure and does not limit the scope of the disclosure unless otherwise required. No language in the specification should be construed as indicating that any non-claimed element is essential to practicing the disclosure.

[0256] All references, including publications, patent applications, and patents, cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.

[0257] In the specification and claims, the terms "coupled" and "connected," as well as their derivatives, may be used. It should be understood that these terms may not be intended as synonyms for each other. On the contrary, in specific 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.

[0258] Unless explicitly stated otherwise, it is to be understood that throughout the specification, terms such as “processing”, “computing”, “calculating”, “determining” and the like refer to the actions and / or processes of a computer or computing system or similar electronic computing device that processes and / or converts data represented as physical quantities (e.g., electronic) in registers and / or memories of the computing system into other data similarly represented as physical quantities in the memories, registers or other such information storage, transmission or display devices of the computing system.

[0259] In a similar manner, the term "processor" may refer to any device or part of a memory that processes electronic data from registers and / or memory and converts the electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" may be a CPU or a GPU. A "computing platform" may include one or more processors. As used herein, a "software" process may include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Similarly, each process may refer to multiple processes to execute instructions sequentially or in parallel, continuously or intermittently. The terms "system" and "method" may be used interchangeably herein, as long as a system may embody one or more methods, and a method may be considered a system.

[0260] In this document, reference may be made to obtaining, acquiring, receiving or inputting analog or digital data into a subsystem, a computer system or a computer-implemented machine. It is possible to obtain, acquire, receive or input analog and digital data in a variety of ways, such as by receiving data as a parameter of a function call or a call to an application programming interface. In some implementations, the process of obtaining, acquiring, 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 obtaining, acquiring, 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. It is also possible to reference 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 accomplished by transmitting data as an input or output parameter of a function call, an application programming interface or an interprocess communication mechanism.

[0261] Although the above discussion sets forth example implementations of the described techniques, other architectures may be used to implement the described functionality and are intended to fall within the scope of the present disclosure. In addition, although specific responsibilities are defined above for discussion purposes, various functions and responsibilities may be allocated and divided in different ways, depending on the circumstances.

[0262] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as exemplary forms of implementing the claims.

Claims

1. A computer-implemented method comprising: receiving an input corresponding to content of a selected portion of a 3D volume corresponding to a first neural radiation field (NeRF) of a scene; generating a second NeRF of the selected portion based at least on the input; and An output NeRF is generated by mixing the first NeRF and the second NeRF.

2. The computer-implemented method of claim 1 , further comprising: determining a characteristic value for a region of the first NeRF; determining an overwrite feature value for the region of the second NeRF; as well as The feature value is replaced by the overwritten feature value in the output NeRF. The computer-implemented method of claim 1 , wherein the input is a text prompt.

4. The computer-implemented method of claim 1 , further comprising: receiving an interaction with the first NeRF, the interaction corresponding to the selected portion; determining a depth of the selected portion based at least on a parameter of the interaction; as well as The selected portion is generated using the depth. The computer-implemented method of claim 1 , wherein the output NeRF is generated by a diffusion model. The computer-implemented method of claim 1 , wherein the input is associated with a tool for making a selection.

7. The computer-implemented method of claim 1 , wherein the selected portion is a two-dimensional selection based on a first camera perspective, the method further comprising: generating one or more rays from a virtual camera associated with the first camera perspective; identifying one or more cells intersected by the one or more rays; as well as A depth of the one or more cells is determined.

8. The computer-implemented method of claim 7, wherein the depth is related to a duration of interaction with the selected portion.

9. The computer-implemented method of claim 1 , further comprising: generating a mask corresponding to the selected portion; as well as The mask is provided to the content generation pipeline.

10. The computer-implemented method of claim 1 , further comprising: rendering the object in an interactive environment; as well as One or more tools are provided in the interactive environment to identify the selected portion.

11. The computer-implemented method of claim 10, wherein the scene and the object are both objects generated using one or more content generation models.

12. A processor, comprising: One or more processing units for: generating a scene representation as a neural radiance field NeRF through one or more diffusion models; receiving an input corresponding to a portion of the NeRF; generating a modified NeRF for the portion based on the indication, the modified NeRF including one or more content portions different from the NeRF; combining the modified NeRF and the NeRF to form an updated NeRF; and A visual representation of the updated NeRF is provided. 13 . The processor of claim 12 , wherein combining the modified NeRF with the NeRF corresponds to overwriting one or more feature values ​​of the NeRF with modified feature values ​​of the modified NeRF.

14. The processor of claim 12, wherein the portion of the NeRF is a three-dimensional (3D) representation generated from a two-dimensional (2D) input and one or more attributes of the 2D input.

15. The processor of claim 12, wherein the indication is at least one of: a text prompt, an auditory prompt, or a feature associated with the input.

16. The processor of claim 12, wherein the processor is included in at least one of: A system for performing simulation operations; Systems for performing simulated operations to test or validate autonomous machine applications; Systems for performing digital twin operations; A system for performing light transport simulations; Systems for rendering graphical output; Systems for performing deep learning operations; Systems implemented using edge devices; Systems for generating or presenting virtual reality (VR) content; Systems for generating or presenting augmented reality (AR) content; Systems for generating or presenting mixed reality (MR) content; A system comprising one or more virtual machines VM; Systems for performing conversational AI application operations; Systems for performing operations of generative AI applications; A system for performing operations using a language model; A system for performing one or more generative content operations using a large language model (LLM); A system implemented at least in part in a data center; A system for performing hardware testing using simulation; A system for performing one or more generative content operations using a language model; Systems for synthetic data generation; A collaborative content creation platform for 3D assets; or A system implemented at least in part using cloud computing resources.

17. A system comprising: One or more processors, including processing circuitry for generating an output representation of a three-dimensional (3D) scene as a combined neural radiation field (NeRF), the combined NeRF comprising an original volume and a modified volume added to the original volume, the modified volume being generated for a selected volume of the original volume based at least on an input corresponding to content of the modified volume.

18. The system of claim 17, wherein objects associated with both the original volume and the modified volume are formed using one or more diffusion models.

19. The system of claim 17, wherein the modified volume is calculated based on a second input corresponding to a two-dimensional region and an attribute of the second input.

20. The system of claim 17, wherein the system comprises at least one of the following: A system for performing simulation operations; Systems for performing simulated operations to test or validate autonomous machine applications; Systems for performing digital twin operations; A system for performing light transport simulations; Systems for rendering graphical output; Systems for performing deep learning operations; Systems implemented using edge devices; Systems for generating or presenting virtual reality (VR) content; Systems for generating or presenting augmented reality (AR) content; Systems for generating or presenting mixed reality (MR) content; A system comprising one or more virtual machines VM; Systems for performing conversational AI application operations; Systems for performing operations of generative AI applications; A system for performing operations using a language model; A system for performing one or more generative content operations using a large language model (LLM); A system implemented at least in part in a data center; Systems that perform hardware testing using simulation; A system for performing one or more generative content operations using a language model; Systems for generating synthetic data; A collaborative content creation platform for 3D assets; or A system implemented at least in part using cloud computing resources.

Images