Abstract: A three-dimensional (3D) animation system automatically assigns accurate animation physics to points of a point cloud to realistically simulate motion of the points in response to different applied forces. The 3D animation system receives the points that are defined with positions in a 3D space and with visual characteristics. The 3D animation system analyzes one or more of the positions and the visual characteristics of the points, classifies the points based on a commonality in the positions or the visual characteristics of the points being associated with a particular classification, and maps a set of animation physics that is defined for the particular classification to the points. The 3D animation system may then animate the points based on the set of animation physics generating an effect in response to a force that is applied to the points.

Abstract: Embodiments are disclosed for optimizing a material graph for replicating a material of the target image. Embodiments include receiving a target image and a material graph to be optimized for replicating a material of the target image. Embodiments include identifying a non-differentiable node of the material graph, the non-differentiable node including a set of input parameters. Embodiments include selecting a differentiable proxy from a library of the selected differentiable proxy is trained to replicate an output of the identified non-differentiable node. Embodiments include generating an optimized input parameters for the identified non-differentiable node using the corresponding trained neural network and the target image. Embodiments include replacing the set of input parameters of the non-differentiable node of the material graph with the optimized input parameters.

Abstract: In one example, an apparatus comprises: a buffer memory; and a memory access circuit configured to: fetch, from a first memory, a set of first groups of data elements of a first matrix, each first group of data elements being stored at consecutive memory addresses at the first memory; based on a first configuration, store the set of first groups of data elements at consecutive memory addresses or at non-consecutive memory addresses at the buffer memory; based on a second configuration that defines a memory address offset, fetch a set of second groups of the data elements from the buffer memory, each second group of the data elements being stored at consecutive memory addresses of the buffer memory, each second group being separated by the memory address offset in the buffer memory; and store each fetched second group at consecutive addresses of a destination memory to form a second matrix.

Abstract: Methods and apparatus relating to scalar core integration in a graphics processor. In an example, an apparatus comprises a processor to receive a set of workload instructions for a graphics workload from a host complex, determine a first subset of operations in the set of operations that is suitable for execution by a scalar processor complex of the graphics processing device and a second subset of operations in the set of operations that is suitable for execution by a vector processor complex of the graphics processing device, assign the first subset of operations to the scalar processor complex for execution to generate a first set of outputs, assign the second subset of operations to the vector processor complex for execution to generate a second set of outputs. Other embodiments are also disclosed and claimed.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for processing a target object. The method includes acquiring an initial non-video feature vector on the basis of at least one input of a received speech input and text input. The method further includes taking, in response to not receiving a video input, a default feature vector as an initial video feature vector corresponding to the video input. The method further includes generating a video feature, a speech feature, and a text feature on the basis of the initial non-video feature vector and the initial video feature vector. The method further includes generating a processing parameter for a target object on the basis of the video feature, the speech feature, and the text feature, wherein the processing parameter includes at least one of an emotion parameter, an attribute parameter, and a pose parameter.

Abstract: An information processing system includes an information processing device, a stream user terminal and viewing user terminal. The information processing device comprises processing circuitry configured to stream a video, including a character object of a stream user, to the viewing user terminal by transmitting information on the video to the viewing user terminal; aggregate resulting information including information on an action by a viewing user to the video during streaming of the video; determine a specific motion to be applied to the character object based on the resulting information; and transmit specific information on the specific motion to the stream user terminal. After the streaming of the video is ended, a resulting screen is displayed on the stream user terminal, the resulting screen including a character image with the specific motion applied to the character object, and the character image is generated based on the specific information.

Abstract: Disclosed is a method for generating a vector diagram. The method is applicable to a field programmable gate array and includes: acquiring video data of an ultra-high definition video system; generating vector diagram data based on the video data; acquiring a pre-generated background image of a vector diagram; and generating the vector diagram based on the background image and the vector diagram data.

Abstract: The present disclosure provides systems and methods for molecular imaging. The systems and methods may obtain, using at least one 3D camera, image data of at least one movable detector of an ECT device. The systems and methods may determine, based on the image data of the at least one movable detector, an arrangement of the at least one insert detector in a coordinate system that relates to the ECT device. The systems and methods may also obtain image data of an object by performing, using the at least one movable detector, an ECT imaging on the object. The systems and methods may generate, based on the arrangement of the at least one movable detector and the image data of the object, an image of the object.

Abstract: A display device includes: a display panel including a first display area and a second display area; and a panel driving block which provides, to the first display area, a first data signal generated by converting a first image signal, which corresponds to the first display area, based on a first reference color coordinates in a color space, and provides, to the second display area, a second data signal generated by converting a second image signal, which corresponds to the second display area, based on second reference color coordinates in the color space. The second reference color coordinates are color coordinates obtained by shifting the first reference color coordinates in the color space.

Abstract: An electronic device may include a first display pipeline that may output image data via an output path. The electronic device may include first frame merge circuitry coupled to the output path. The electronic device may also include a first multiplexer coupled to the first frame merge circuitry and to the output path. The first multiplexer may transmit the image data from the output path to an electronic display, and, in response to a first control signal associated with the first frame merge circuitry generating a merged output, the first multiplexer transmits the merged output to the electronic display.

Abstract: A digital asset management system is enhanced with an end-to-end deep zoom feature functionality that receives a user request to generate a deep zoom image of an asset, performs an image conversion if necessary, generates the deep zoom image and stores corresponding image folders and files in a transient storage separate from assets managed by the digital asset management system, and cleans up the deep zoom files after a pre-configured time period. The deep zoom image is rendered directly from the transient storage without having to involve the repository, which is separately managed by the digital asset management system. A new Web context is created and provided for viewing the deep zoom image within a browser-based user interface of the digital asset management system for a seamless user experience.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for generating, in a display panel, a virtual mask layer around a cutout region for a front camera. The front camera may be positioned under the display panel and receive light through the cutout region. The mask layer may hide defects of the cutout region that does not have functional pixels. The disclosed techniques may improve aesthetic appearance of displays having punch-hole cameras with reduced hole sizes and increased production quality conformance rate.

Abstract: An image copying assistant is a computing application configured to aid users in copying a digital image to a physical canvas using traditional media on the physical canvas. The image copying assistant utilizes augmented reality techniques to present features of the digital image projected onto the physical canvas. The image copying assistant detects previously generated markers in an output of a digital image sensor of a camera of a computing device and use the detected markers to calculate the plane and boundaries of the surface of the physical canvas. The image copying assistant uses the calculated plane and boundaries to determine a position of the digital image on a display of the computing device.

Abstract: Embodiments are directed toward apparatuses, systems, and methods to implement policies for dynamically switching between an integrated graphics mode and a discrete graphics mode for providing a display signal to an external USB Type-C port. Some embodiments include a controller configured to provide signals to a first multiplexer and to a second multiplexer, and based on a platform policy, control the at least first or the second multiplexer to dynamically switch to the first graphics mode to output signals received from an integrated graphics controller to the external USB Type-C port or to switch to the second graphics mode to output signals received from a discrete graphics controller to the external USB Type-C port. Other embodiments may be described and/or claimed.

Abstract: An image processing method includes detecting pointer contact positions trajectories on a display surface, displaying a first image on the display surface, displaying a second image having first and second portions on the display surface using the first image as a background, moving a second image display position on the display surface along the pointer trajectory when a pointer trajectory starting point is included in a display surface area on which the second image is displayed, providing a drawing effect to a first image portion overlapping a second image trajectory when the starting point is included in an area in which the first portion is displayed in the moving the second image display position, and keeping the first image portion display overlapping the second image trajectory when the starting point is included in an area in which the second portion is displayed in the moving the second image display position.

Abstract: Methods and hardware for texture address generation comprise receiving fragment coordinates for an input block of fragments and texture instructions for the fragments and calculating gradients for at least one pair of fragments. Based on the gradients, the method determines whether a first mode or a second mode of texture address generation is to be used and then uses the determined mode and the gradients to perform texture address generation. The first mode of texture address generation performs calculations at a first precision for a subset of the fragments and calculations for remaining fragments at a second, lower, precision. The second mode of texture address generation performs calculations for all fragments at the first precision and if the second mode is used and more than half of the fragments in the input block are valid, the texture address generation is performed over two clock cycles.

Abstract: A display type vehicle switch operating apparatus includes a receiver that receives driving information related to an external driving situation of a vehicle and display state information of a display of the vehicle, a highlight indication information generator that generates highlight indication information of a symbol displayed on the display based on the received driving information and the received display state information, and a controller that highlights the symbol displayed on the display based on the generated highlight indication information.

Abstract: Technologies are described for reconstructing facial models which are preserved images or images captured from security cameras. The reconstructed models can be three-dimensional (3D) point clouds and can be compared to existing facial models and/or other reconstructed models based on physical geometry. The 3D point cloud models can be encoded into one or more latent space feature vector representations which can allow both local and global geometric properties of a face to be described. The one or more feature vector representations of a target face can be used individually or in combination with other descriptors for recognition, retrieval, and classification tasks. Neural networks can be used in the encoding of the one or more feature vector representations.

Abstract: A graphics processing unit (GPU) of a processing system transmits pixel data for a frame to a display in a compressed burst, so that the pixel data is communicated at a rate that is higher than the rate at which the display scans out the pixel data to refresh the frame at a display panel. By transmitting pixel data for the frame in a compressed burst, the GPU shortens the time spent transmitting the pixel data and extends the time before the next frame of pixel data is to be transmitted. During the extended time before the next frame of pixel data is to be transmitted, the GPU saves power by placing portions of the processing system in a reduced power mode.

Abstract: Techniques are disclosed relating to operand routing among SIMD pipelines. In some embodiments, an apparatus includes a set of multiple hardware pipelines configured to execute a single-instruction multiple-data (SIMD) instruction for multiple threads in parallel, wherein the instruction specifies first and second architectural registers. In some embodiments, the pipelines include execution circuitry configured to perform operations using one or more pipeline stages of the pipeline. In some embodiments, the pipelines include routing circuitry configured to select, based on the instruction, a first input operand for the execution circuitry from among: a value from the first architectural register from thread-specific storage for another pipeline and a value from the second architectural register from thread-specific storage for a thread assigned to another pipeline.