Abstract: A medical image processing device includes: image acquisition unit configured to acquire image information obtained by imaging with a medical observation device; and superimposed image generation circuitry configured to generate a superimposed image in which a pattern image having first images with a specific shape arranged in parallel in a specific pattern and a captured image based on the image information are superimposed on each other.

Abstract: In various examples, to support training a deep neural network (DNN) to predict a dense representation of a 3D surface structure of interest, a training dataset is generated using a parametric mathematical modeling. A variety of synthetic 3D road surfaces may be generated by modeling a 3D road surface using varied parameters to simulate changes in road direction and lateral surface slope. In an example embodiment, a synthetic 3D road surface may be created by modeling a longitudinal 3D curve and expanding the longitudinal 3D curve to a 3D surface, and the resulting synthetic 3D surface may be sampled to form a synthetic ground truth projection image (e.g., a 2D height map). To generate corresponding input training data, a known pattern that represents which pixels may remain unobserved during 3D structure estimation may be generated and applied to a ground truth projection image to simulate a corresponding sparse projection image.

Abstract: Some implementations relate to methods, systems, and computer-readable media for automatically capturing training data. In some implementations, a computer-implemented method includes generating a respective set of descriptors based on content identified in a 3D model, presenting, in a user interface, the 3D model and two or more descriptors, receiving, from the user interface, at least one selection from the two or more descriptors, authenticating a user based on the at least one selection, and modifying a weight of at least one descriptor associated with the at least one selection for an associated 2D image in a labeled training set for an artificial intelligence (AI) model.

Abstract: Systems, apparatuses, and methods for performing dead surface invalidation are disclosed. An application sends draw call commands to a graphics processing unit (GPU) via a driver, with the draw call commands rendering to surfaces. After it is determined that a given surface will no longer be accessed by subsequent draw calls, the application sends a surface invalidation command for the given surface to a command processor of the GPU. After the command processor receives the surface invalidation command, the command processor waits for a shader engine to send a draw call completion message for a last draw call to access the given surface. Once the command processor receives the draw call completion message, the command processor sends a surface invalidation command to a cache to invalidate cache lines for the given surface to free up space in the cache for other data.

Abstract: One embodiment provides for a graphics processing unit to perform computations associated with a neural network, the graphics processing unit comprising a hardware processing unit having a dynamic precision fixed-point unit that is configurable to convert elements of a floating-point tensor to convert the floating-point tensor into a fixed-point tensor.

Abstract: Systems, apparatuses, and methods for implementing register compaction with early release are disclosed. A processor includes at least a command processor, a plurality of compute units, a plurality of registers, and a control unit. Registers are statically allocated to wavefronts by the control unit when wavefronts are launched by the command processor on the compute units. In response to determining that a first set of registers, previously allocated to a first wavefront, are no longer needed, the first wavefront executes an instruction to release the first set of registers. The control unit detects the executed instruction and releases the first set of registers to the available pool of registers to potentially be used by other wavefronts. Then, the control unit can allocate the first set of registers to a second wavefront for use by threads of the second wavefront while the first wavefront is still active.

Abstract: A method of detecting an error at a graphics processing unit causes an instruction including a request for a response from a graphics processing unit to be provided to the graphics processing unit. A timer being configured to expire after a time period is initialised, and during the time period the graphics processing unit is monitored for the response from the graphics processing unit. An error is determined to have occurred in response to determining that no response was received from the graphics processing unit before the timer expired.

Abstract: A location-based metaverse social media system provided for users to actually move and carry out various social events of online/offline interactions after positioning through a mobile device includes a virtual world management processor and an user processor. The virtual world management processor is provided for augmenting a plurality of parallel virtual worlds by basic map information of the real world and the user processor is provided for the users to create personal accounts and a virtual character tied with them and displayed on the mobile device. In operations, the users can switch to any one of the parallel virtual worlds in a cross-world manner and perform a location-based social event while the users are moving.

Abstract: A vehicle device includes an application as a determiner configured to determine whether a frame buffer has been updated. The application is further configure to set a determination region, prepare a determination image to be drawn in the determination region, request a GPU to draw the prepared determination image, read the determination image that is actually drawn in the frame buffer by the GPU, and determine that the frame buffer has been updated when the prepared determination image matches the read determination image.

Abstract: Various implementations disclosed herein include devices, systems, and methods that use an analytic approach to determine signed distance field (SDF) representations that represent one or more curves (e.g., glyphs that represent text) and cache the SDF representations for reuse in rendering the curves in similar rendering conditions. For example, the SDF representation may be re-used, based on determining that text is going to occupy a similar-sized portion of the device's display in multiple views. An SDF representation is recalculated if different conditions (e.g., substantial zooming in on the text) occur in different views.

Abstract: The present application provides a bridge supply circuit of a multipath Efuse chip and a server. The supply circuit includes: a first Efuse chip and multiple second Efuse chips, inputs of the first Efuse chip and the multiple second Efuse chips being connected to a power supply, an output of the first Efuse chip being connected to each of the Graphics processing units (GPUs), an output of each of the multiple second Efuse chips being separately connected to each of the GPUs except for a first GPU; damping circuits, each of the damping circuits being separately provided between the output of each of the multiple second Efuse chips and the GPU; and current paths, each of the current paths being separately provided between the output of the first Efuse chip and each of the GPUs except for the first GPU.

Abstract: Systems and methods are provided for determining a first upper bound of a x-direction frame margin of a downsampled image and a second upper bound for a y-direction frame margin of the downsampled image. A total value for each row and column of a weighted grayscale image formed from the downsampled image may be determined. An outlier filtering may be applied to the determined total values for each row and column of the weighted grayscale image. A peak of pairwise ratios of consecutive values from left and right sides of the weighted grayscale image may be used to determine an x-margin, and a peak of pairwise ratios of consecutive values from top and bottom sides of the weighted grayscale image may be used to determine a y-margin. Content may be applied to the image based on the determined x-margin and y-margin values to form a composite image.

Abstract: Disclosed a method and a system for overlapping sliding window segmentation of an image based on an FPGA. According to the method, on-chip BRAMs storage resource cost of FPGA is determined; each on-chip BRAM in FPGA is used to cache the pixel data of each segmented sub-image in parallel; when the pixel data received by the BRAMs reaches a preset threshold or the last pixel of the segmented sub-image is written into the on-chip BRAMs, the data is written from the on-chip BRAMs to an off-chip DDR memory in a burst continuous writing mode; the repeated data generated by segmentation of horizontally overlapping sliding windows are written into the on-chip BRAMs corresponding to the current segmented sub-image and adjacent segmented sub-images thereof respectively in a synchronous and parallel manner.

Abstract: An electronic apparatus performs a method of real time simulation of physical visual effect on one or more Graphics Processing Units (GPUs). The method includes a plurality of time steps. Each of the time steps includes: building up a mapping between particles and background grid blocks; sorting the particles to a level of granularity; transferring momenta and masses of the particles to grid nodes on the background grid blocks to compute forces on the grid nodes; updating velocities and resolving collisions from the computed forces on the grid nodes; and applying the updated velocities back to the particles from the grid nodes and advecting the particles. In some embodiments, the frequency of building up and sorting is reduced compared with the frequency of transferring, updating, and applying in the plurality of time steps.

Abstract: In various examples, to support training a deep neural network (DNN) to predict a dense representation of a 3D surface structure of interest, a training dataset is generated using a parametric mathematical modeling. A variety of synthetic 3D road surfaces may be generated by modeling a 3D road surface using varied parameters to simulate changes in road direction and lateral surface slope. In an example embodiment, a synthetic 3D road surface may be created by modeling a longitudinal 3D curve and expanding the longitudinal 3D curve to a 3D surface, and the resulting synthetic 3D surface may be sampled to form a synthetic ground truth projection image (e.g., a 2D height map). To generate corresponding input training data, a known pattern that represents which pixels may remain unobserved during 3D structure estimation may be generated and applied to a ground truth projection image to simulate a corresponding sparse projection image.

Abstract: Systems and methods to reconfigure a scene based on timing and scene content are disclosed. Exemplary implementations may: obtain scene information defines a scene in which an event transpires; analyze the scene information that defines the event to identify effectual content and ineffectual content related to the event within the unedited event duration; and generate, based on the scene information and the analysis, a draft scene that includes an edited event comprising the effectual content from an edited event beginning to an edited event end in accordance with the prospective event duration.

Abstract: Devices, systems, and methods for augmented reality in surgical environments include an optical lens, which may be wearable by the user, and an augmented reality control system for generating an augmented reality presentation in the optical lens. The augmented reality presentation can depict the surgical area of the patient while artificially omitting one or more obstructions from the user's view point of the surgical area.

Abstract: An apparatus, such as a graphical processing unit (GPU), includes one or more processors configured to determine a plurality of first locality information of a received wave at a processing unit and to select a first processing element of a plurality of processing elements, the first processing unit having a plurality of second locality information from a previous wave that matches the plurality of first locality information to execute the received wave.

Abstract: An image display method includes drawing a first graph in a trusted execution environment (TEE). The method also includes displaying the first graph on a first layer in a display screen. The method further includes drawing a second graph in a rich execution environment (REE). The method additionally includes displaying the second graph on a second layer in the display screen. The first layer is located above the second layer. The first graph includes a transparent area and a non-transparent area. The non-transparent area includes content drawn in the TEE. A display area that is on the second graph and that corresponds to the transparent area includes content drawn in the REE. When the first layer and the second layer are overlapped for displaying, the transparent area does not shield the content drawn in the REE.

Abstract: Systems, methods, and techniques dynamically utilize load balancing for workgroup assignments between a group of shader engines by a command processor of a graphics processing unit (GPU). Based on one or more commands received for execution, a plurality of workgroups is generated for assignment to a plurality of shader engines for processing, each shader engine including a respective quantity of active compute units. Each workgroup of the plurality of workgroups is dynamically assigned to a respective shader engine for execution based at least in part on indications of available resources respectively associated with each of the shader engines. In various embodiments, the indications of available resources may include physical parameters regarding each shader engine, as well as current status information regarding the processing of workgroups assigned to each shader engine.