31results about "Details involving image processing hardware" patented technology

Techniques are described for implementing selective activation and deactivation of a dynamically allocated subset of shader engines, such as based on application-based profile information and / or on an active system power configuration. Instructions for execution are received from an application associated with a first application profile.Based on the application profile, a quantity of activated shader engines in a plurality of shader engines is modified. The quantity of activated shader engines is further modified responsive to receiving additional instructions from a second application, and / or to receiving one or more indications of an altered active system power configuration.

Graphics processor (2) comprises a programmable execution unit (65) executing programs to perform graphics processing and a machine learning (ML) processing circuit (78) (e.g. neural processing accele

The present invention specifically relates to a system and method for reconstructing microscope images, such as phase contrast microscope images, using a convolutional neural network, such as a U-net convolutional neural network. The method according to the present invention comprises the steps of obtaining a training data set comprising a plurality of bright field microscope images and a plurality of phase contrast microscope images, training a neural network based on the data set to extract phase information in the form of an interference pattern from each of the plurality of bright field microscope images, and further using the trained neural network to reconstruct a phase contrast microscope image from a bright field microscope image. The system according to the present invention comprises a memory device, a processing device, a storage and retrieval device, and a display device. The memory device stores the data set, the processing device trains a neural network based on the data set, and further enables the reconstruction of a phase contrast image.

Embodiments of the present disclosure provide for implementing a mixed reality system with less power. In some examples, a passive state of the mixed reality system can have a GPU render predictable content that does not need to be processed by a CPU. In such examples, the predictable content can be identified and rendered by the GPU while the CPU is in a low-power mode. Accordingly, embodiments of the present disclosure provide benefits not available with conventional techniques because a CPU may consume more power than a corresponding GPU. In some examples, the passive state can take advantage of the fact that predictable content can be identified and rendered without the use of the CPU. In such examples, the passive state can render predictable content that does not need to be processed by the CPU.

The present disclosure provides a system and method for image reconstruction. The method may include obtaining image raw data; determining, based on a complexity of a reconstruction task of the image raw data and processing capacities of one or more workstations, from the one or more workstations, one or more hardware resources for processing the image raw data; generating, based on the image raw data and the one or more hardware resources, one or more sub tasks of the reconstruction task; assigning the one or more sub tasks to the one or more hardware resources; obtaining one or more intermediate results corresponding to the one or more sub tasks, the one or more intermediate results being generated by the one or more hardware resources; and generating, based on the one or more intermediate results, a reconstruction result of the image raw data.

In a general aspect, enhancement of artificial intelligence algorithms using 3D data is described. In some aspects, input data of an object is stored in a storage engine of a system. The input data includes first-order primitives and second-order primitives. A plurality of features of the object is determined by operation of an analytics engine of the system, based on the first-order primitives and the second-order primitives. A tensor field is generated by operation of the analytics engine of the system. The tensor field includes an attribute set, which includes one or more attributes selected from the first-order primitives, the second-order primitives, or the plurality of features. The tensor field is processed by operation of the analytics engine of the system according to a series of artificial intelligence algorithms to generate output data representing the object.

Systems and techniques are described herein for foveated imaging. For instance, a method for foveated imaging is provided. The method may include obtaining foveated image data comprising first image data representative of a first field of view (FOV) of a scene at a first resolution and second image data representative of a second FOV of the scene at a second resolution, wherein the first FOV is smaller than the second FOV and wherein the first resolution is higher than the second resolution; determining that a user is gazing at virtual content; based on determining that the user is gazing at the virtual content, disabling output of the first image data; and outputting the second image data to a computing device.

This disclosure describes supporting distributed graphics and compute engines in a multi-dielet processor, such as, for example, a multi-dielet graphics processing unit (GPU), architectures and synchronization in such architectures. Each multi-dielet processor includes a hardware-implemented remapping capability and / or a hardware-implemented memory barrier capability.

A processing device, that communicates with an ultrasound device, includes: a display screen; a memory that stores presets, where each preset includes one or more modes used to control the ultrasound device and one or more tools to analyze ultrasound data from the ultrasound device; and a processor coupled to the memory. The processor is configured to: operate the ultrasound device using a first preset; generate ultrasound images using ultrasound data from the ultrasound device, where the ultrasound images include a first portion of the ultrasound images that are imaging frames acquired with the first preset and a second portion of the ultrasound images that are search frames acquired with a search preset; display the imaging frames of the first portion on the display screen; identify an anatomical feature in the search frames using a deep learning model; select a target preset based on the identified anatomical feature.

Ensuring reproducibility in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit ('GPU') servers, including: identifying, by a unified management plane, one or more transformations applied to a dataset by the artificial intelligence infrastructure, wherein applying the one or more transformations to the dataset causes the artificial intelligence infrastructure to generate a transformed dataset; storing, within the one or more storage systems, information describing the dataset, the one or more transformations applied to the dataset, and the transformed dataset; identifying, by the unified management plane, one or more machine learning models executed by the artificial intelligence infrastructure using the transformed dataset as input; and storing, within the one or more storage systems, information describing one or more machine learning models executed using the transformed dataset as input.

An image processing device includes a processor and a memory that is connected to or provided in the processor. The processor acquires a plurality of tomographic images which indicate a plurality of tomographic planes of an object, respectively, and have a first resolution, sets a partial region of the tomographic image as a target region in a case in which an operation instruction related to interpretation is received from a user, performs a process of converting a resolution into a second resolution higher than the first resolution only on the target region to generate a high-resolution partial image of the target region, and displays the high-resolution partial image.

Techniques and systems are provided for processing image data using one or more neural networks. For example, a patch of raw image data can be obtained. The patch can include a subset of pixels of a frame of raw image data, and the frame can be captured using one or more image sensors. The patch of raw image data includes a single color component for each pixel of the subset of pixels. At least one neural network can be applied to the patch of raw image data to determine a plurality of color component values for one or more pixels of the subset of pixels. A patch of output image data can then be generated based on application of the at least one neural network to the patch of raw image data. The patch of output image data includes a subset of pixels of a frame of output image data, and also includes the plurality of color component values for one or more pixels of the subset of pixels of the frame of output image data. Application of the at least one neural network causes the patch of output image data to include fewer pixels than the patch of raw image data. Multiple patches from the frame can be processed by the at least one neural network in order to generate a final output image. In some cases, the patches from the frame can be overlapping so that the final output image contains a complete picture.

The application discloses a binocular stereo matching hardware architecture supporting variable disparity range, which can realize real-time switching of disparity working range in work by configuring a cost calculation and aggregation module through a disparity range switching controller without changing algorithm processing details, can switch the disparity range worked by hardware according to different application scenarios, performs different disparity range calculation in different working scenarios, and supports a working environment requiring a large disparity range while the hardware can work in a small disparity range mode in an open outdoor scene, so that the calculation amount is greatly reduced, and the working power consumption of the overall hardware is reduced.

A command for causing a graphics processor to perform processing work for a graphics processing pipeline that the graphics processor can execute. A command to perform processing work for the graphics processing pipeline includes a first portion including a generic opcode that can be interpreted by a command processing circuit of the graphics processor to identify that the command is a command to perform processing work for the graphics processing pipeline and a second portion that is not used by command processing circuit but identifies to the graphics processing pipeline the particular processing operations to be performed. The first portion also includes information indicating a set of zero or more data values to be used for one or more processing operations for the graphics processing pipeline.

A graphics processing system that is operable to perform ray tracing is disclosed. It may be determined whether a ray may intersect geometry associated with a node by testing the ray against two different types of geometric object associated with the node: a first type that defines the volume that the node represents, and a second, different type that defines a region of the volume that the node represents within which geometry does not fall.

Aspects presented herein relate to methods and devices for graphics processing, including an apparatus such as a GPU. The apparatus may receive a plurality of pixels associated with a first color space including a plurality of first color channels, where at least one first color channel of the plurality of first color channels is a first compressed channel. The apparatus may also decompress the at least one first color channel of the plurality of first color channels, where the at least one first color channel is decompressed from the first compressed channel to a first decompressed channel. Furthermore, the apparatus may perform a color space conversion of the first color space associated with the plurality of pixels, such that the plurality of first color channels are converted to a plurality of second color channels, where the plurality of second color channels are associated with a second color space for the plurality of pixels.

Hardware tessellation units include a sub-division logic block that comprises hardware logic arranged to perform a sub-division of a patch into two (or more) sub-patches. The hardware tessellation units also include a decision logic block that is configured to determine whether a patch is to be sub-divided or not and one or more hardware elements that control the order in which tessellation occurs. In various examples, this hardware element is a patch stack that operates a first-in-last-out scheme and in other examples, there are one or more selection logic blocks that are configured to receive patch data for more than one patch or sub-patch and output the patch data for a selected one of the received patches or sub-patches.

A tiling unit assigning primitives to tiles in a graphics processing system which has rendering space subdivided into a plurality of tiles. Each tile can comprise one or more polygonal region. Mesh logic of the tiling unit can determine that a plurality of primitives form a mesh and can determine whether the mesh entirely covers a region. If the mesh entirely covers the region then a depth threshold for the region can be updated so that subsequent primitives which lie behind the depth threshold are culled (i.e. not included in the display list for a tile). This helps to reduce the number of primitive IDs included in a display list for a tile which reduces the amount of memory used by the display list and reduces the number of primitives which a hidden surface removal (HSR) module needs to fetch to perform HSR on the tile.

This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for dynamic wave pairing. A graphics processor may allocate one or more GPU workloads to one or more wave slots of a plurality of wave slots. The graphics processor may select a first execution slot of a plurality of execution slots for executing the one or more GPU workloads. The selection may be based on one of a plurality of granularities. The graphics processor may execute, at the selected first execution slot, the one or more GPU workloads at the one of the plurality of granularities.

Methods and systems integrate digital fingerprint authentication-based identification and location tracking into a single, continuous process in which an authentication-integrated tracking system is simultaneously aware of both the identity and location of each physical object at all times as they move along a conveyance system. Insertion or removal of an object is quickly detected and reported. Rapid reestablishment and continuation of authentication-integrated tracking is enabled in the event of any temporary interruption or failure of tracking in the system. An exemplary system comprises plural tracking units networked together, each tracking unit including a camera or scanner to observe a corresponding field of view, the tracking units arrange to realize a continuous field of view of a physical conveyance system.

A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

A system (100), method, and computer program product for direct multi-volume rendering. The 3D data specifies a three-dimensional scene having multiple volumes (290). Each voxel in a particular volume has a scalar value that is the result of an imaging procedure for measuring physical properties of the imaged subject. A multi-ray generator (230) generates a view multi-ray in the direction of a particular pixel in the projection image, which represents the 2D projection of all scene voxels intersected by the view multi-ray after the projection image. A volume ray marching processor (240) processes each view ray in its associated volume using volume ray marching, and at each ray marching step, the scalar value of a corresponding voxel is mapped to the color and transparency values ​​of the corresponding voxel. A projection image updater (250) updates the value of a particular pixel in the projection image by combining the color and transparency values ​​of each voxel in each view ray. Updating the value of a particular voxel intersecting a particular view ray is performed after updating the values ​​of all intersecting voxels that are closer to the viewpoint than the particular voxel.

Frames are rendered in a graphics processing unit representing views of a scene in a rendering space subdivided into a plurality of tiles. Tiles of a group of frames are rendered in an interspersed order such that the frame from which a tile is rendered switches back and forth between the frames of the group of frames, wherein the view represented by each frame in the group of frames is a view of the scene at a different time instance, wherein at least one transformation indicates tiles which are likely to be similar in different frames of the group of frames, wherein the interspersed order is based on the at least one transformation such that said rendering comprises rendering similar tiles from the frames of the group of frames sequentially.

Systems and techniques are described herein for foveated imaging. For instance, a method for foveated imaging is provided. The method may include obtaining foveated image data comprising first image data representative of a first field of view (FOV) of a scene at a first resolution and second image data representative of a second FOV of the scene at a second resolution, wherein the first FOV is smaller than the second FOV and wherein the first resolution is higher than the second resolution; determining that a user is gazing at virtual content; based on determining that the user is gazing at the virtual content, disabling output of the first image data; and outputting the second image data to a computing device.

The application discloses a Direct3D 12 depth offset semantic implementation method based on shader compensation, and when GPU does not support VK_EXT_depth_bias_control, the system starts after the kernel level detects GPU depth offset characteristics, and builds an adaptive strategy and stores it in the kernel state buffer; after VKD3D and application start, the first history buffer and three-level PSO cache are created by VKD3D; when the application creates a shader and creates a D3D12 PSO, the VKD3D extracts parameters, compiles a Vulkan shader module, analyzes depth offset parameters, queries an adaptive strategy, and generates a corresponding type of shader variant; a PSO fixed template is built, a cache key is generated to query a PSO dynamic variant in the three-level PSO cache, a PSO dynamic variant is bound when a pipeline state is set in the application, and after a drawing instruction is submitted, a Vulkan command buffer is submitted to the GPU to complete rendering.