Abstract: A technique is described for extracting or constructing a three-dimensional (3D) model from multiple two-dimensional (2D) images. In an embodiment, a foreground segmentation mask or depth field may be provided as an additional supervision input with each 2D image. In an embodiment, the foreground segmentation mask or depth field is automatically generated for each 2D image. The constructed 3D model comprises a triangular mesh topology, materials, and environment lighting. The constructed 3D model is represented in a format that can be directly edited and/or rendered by conventional application programs, such as digital content creation (DCC) tools. For example, the constructed 3D model may be represented as a triangular surface mesh (with arbitrary topology), a set of 2D textures representing spatially-varying material parameters, and an environment map. Furthermore, the constructed 3D model may be included in 3D scenes and interacts realistically with other objects.

Abstract: An image has pixels arranged in perpendicular rows/columns. The size of the image is changed to produce a changed-size image and the changed-size image is output. The process of changing the size of the image adds at least one row/column as at least one inserted row/column. The inserted row/column is made up of data from generating adjacent rows/columns of the perpendicular rows/columns. Embodiments that reduce the size of the image remove the generating adjacent rows/columns that were used to form the inserted row/column and, in such reduction processing the inserted row/column is added where the (now removed) generating adjacent rows/columns were previously positioned. In embodiments that increase the size of the image, instead of removing the generating adjacent rows/columns, the inserted row/column is merely inserted between the adjacent rows/columns.

Abstract: An electronic device includes a first display driver configured to control a first display, a second display driver configured to control a second display, and a processor. The processor is configured to: if screen switching is detected while displaying first image data on the first display using a first pixel value, produce a first calibration value based on the difference between the first pixel value for display on the first display and a second pixel value for display on the second display; apply the first calibration value to the second pixel value so as to produce a third pixel value corresponding to the first pixel value; and control the second display driver so as to display the first image data on the second display using the third pixel value. Various other embodiments may be provided.

Abstract: A neural processor. In some embodiments, the processor includes a first tile, a second tile, a memory, and a bus. The bus may be connected to the memory, the first tile, and the second tile. The first tile may include: a first weight register, a second weight register, an activations buffer, a first multiplier, and a second multiplier. The activations buffer may be configured to include: a first queue connected to the first multiplier and a second queue connected to the second multiplier. The first queue may include a first register and a second register adjacent to the first register, the first register being an output register of the first queue. The first tile may be configured: in a first state: to multiply, in the first multiplier, a first weight by an activation from the output register of the first queue, and in a second state: to multiply, in the first multiplier, the first weight by an activation from the second register of the first queue.

Abstract: Examples described herein relate to a graphics processing system that includes one or more integrated graphics systems and one or more discrete graphics systems. In some examples, an operating system (OS) or other software supports switching between image display data being provided from either an integrated graphics system or a discrete graphics system by configuring a multiplexer at runtime to output image data to a display. In some examples, a multiplexer is not used and interface supported messages are used to transfer image data from an integrated graphics system to a discrete graphics system and the discrete graphics system generates and outputs image data to a display. In some examples, interface supported messages are used to transfer image data from a discrete graphics system to an integrated graphics system and the integrated graphics system uses an overlay process to generate a composite image for output to a display.

Abstract: A tool allows a user to create new designs for apparel and preview these designs in three dimensions before manufacture. Software and lasers are used in finishing apparel to produce a desired wear pattern or other design. Based on a laser input file with a pattern, a laser will burn the pattern onto apparel. With the tool, the user will be able to create, make changes, and view images of a design, in real time, before burning by a laser. Input to the tool includes fabric template images, laser input files, and damage input. The tool allows adding of tinting and adjusting of intensity and bright point. The user can also move, rotate, scale, and warp the image input.

Abstract: A weighted average execution time associated with each execution stage of a plurality of execution stages used to process a plurality of frames in parallel is obtained. The processing of each of the plurality of frames is performed at each of the plurality of execution stages in a sequential order, starting with an initial execution stage and continuing with each subsequent execution stage. A first largest weighted average execution time associated with one of the plurality of execution stages is determined. A delay to the initial execution stage prior to processing a first next frame is applied. The delay is determined based on the first largest weighted average execution time.

Abstract: Various embodiments set forth systems and techniques for generating seams for a 3D model. The techniques include generating, based on the 3D model, one or more inputs for one or more trained machine learning models; providing the one or more inputs to the one or more trained machine learning models; receiving, from the one or more trained machine learning models, seam prediction data generated based on the one or more inputs; and placing one or more predicted seams on the 3D model based on the seam prediction data.

Abstract: The disclosed technology generally relates to a graphics processing unit (GPU). In one aspect, a GPU includes a general purpose register (GPR) having registers, an arithmetic logic unit (ALU) configured to read pixels of an image independently of a shared memory, and a level 1 (L1) cache storing the pixels read by the ALU. The ALU can implement pixel mapping by fetching a quad of pixels, which includes pixels of first, second, third, and fourth pixel types, from the L1 cache, grouping the pixels of the different pixel types of the quad into four groups based on pixel type, and, for each group, separating the pixels included in the group into three regions that each have a set of pixels. The pixels for each group can then be loaded into the registers corresponding to the three regions.

Abstract: A method and system for a command processor for efficient processing of a program multi-processor core system with a CPU and GPU. The multi-core system includes a general purpose CPU executing commands in a CPU programming language and a graphic processing unit (GPU) executing commands in a GPU programming language. A command processor is coupled to the CPU and CPU. The command processor sequences jobs from a program for processing by the CPU or the GPU. The command processor creates commands from the jobs in a state free command format. The command processor generates a sequence of commands for execution by either the CPU or the GPU in the command format. A compiler running a meta language converts program data for the commands into a first format readable by the CPU programming language and a second format readable by the GPU programming language.

Abstract: Systems and methods are disclosed for aligning a two-dimensional (2D) design image to a 2D projection image of a three-dimensional (3D) design model. One method comprises receiving a 2D design document, the 2D design document comprising a 2D design image, and receiving a 3D design file comprising a 3D design model, the 3D design model comprising one or more design elements. The method further comprises generating a 2D projection image based on the 3D design model, the 2D projection image comprising a representation of at least a portion of the one or more design elements, generating a projection barcode based on the 2D projection image, and generating a drawing barcode based on the 2D design image. The method further comprises aligning the 2D projection image and the 2D design image by comparing the projection barcode and the drawing barcode.

Abstract: The present disclosure is generally directed to reconstructing representations of bodies from images. An example method of the present disclosure includes inputting, into a machine-learned reconstruction model, input data descriptive of an image depicting a body; predicting, using a machine-learned marker prediction component of the reconstruction model, a set of surface marker locations on the body; and outputting, using a machine-learned marker poser component of the reconstruction model, an output representation of the body that corresponds to the set of surface marker locations. In the example method, one or more parameters of the reconstruction model were learned at least in part based on a consistency loss corresponding to a distance between relaxed-constraint representations generated from a prior set of surface marker locations predicted according to the one or more parameters and parametric representations generated from the prior set using kinematic constraints associated with the body.

Abstract: Electronic device depth camera systems having a reduced number of outwardly-facing optical components are disclosed. Monocular depth camera systems, including basic depth camera systems as well as RGB-D camera systems, have exactly one window on a housing panel of the device through which light is transmittable out of and into the device housing. An optical emitter and detector(s) are located within the device housing. Binocular RGB-D camera systems have exactly two outwardly-facing optical components on the housing panel. One of the components, such as an optical emitter or an exit window, is associated with illumination light leaving the device, and the other optical component is an entrance window associated with transmitting detection light into the housing.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: A method of completing coloring of an image based on a query regarding a color-unknown region in the image and an answer to the query, includes: generating, by using an artificial neural network, a first intermediate image in which at least one uncolored region in a primary image is colored; generating, by using the artificial neural network, a first color query regarding the at least one color-unknown region in the primary image; and generating a secondary image based on at least one of the first color query, a first answer to the first color query, and the first intermediate image.

Abstract: One example method involves operations for receiving a request to transform an input image into a target image. Operations further include providing the input image to a machine learning model trained to adapt images. Training the machine learning model includes accessing training data having a source domain of images and a target domain of images with a target style. Training further includes using a pre-trained generative model to generate an adapted source domain of adapted images having the target style. The adapted source domain is generated by determining a rate of change for parameters of the target style, generating weighted parameters by applying a weight to each of the parameters based on their respective rate of change, and applying the weighted parameters to the source domain. Additionally, operations include using the machine learning model to generate the target image by modifying parameters of the input image using the target style.

Abstract: Implementing heterogeneous wavefronts on a graphics processing unit (GPU) is disclosed. A scheduler assigns heterogeneous wavefronts for execution on a compute unit of a processing device. The heterogeneous wavefronts include different types of wavefronts such as vector compute wavefronts and service-level wavefronts that vary in resource requirements and instruction sets. As one example, heterogeneous wavefronts may include scalar wavefronts and vector compute wavefronts that execute on scalar units and vector units, respectively. Distinct sets of instructions are executed for the heterogeneous wavefronts on the compute unit. Heterogeneous wavefronts are processed in the same pipeline of the processing device.

Abstract: According to at least one embodiment, a method for generating a mesh deformation of a facial model includes: generating a first plurality of deformation maps by applying a first plurality of neural network-trained models; extracting a first plurality of vertex offsets based on the first plurality of deformation maps; and applying the first plurality of vertex offsets to a neutral mesh of the facial model to generate the mesh deformation of the facial model.

Abstract: A graphics processing unit (GPU) instructs a display control module to capture content and display captured content in response to the refresh rate of a display exceeding a frame generation rate of the GPU. Rather than re-transmit the same frame multiple times, the GPU instructs the display control module to replay a previously-transmitted frame. During a refresh cycle in which the display control module is replaying captured content, the GPU omits accessing memory to retrieve and resend the frame that is being replayed, and instead sends only invalid data and GPU timing information so that the display control module remains synchronized with the GPU.

Abstract: A computing device includes one or more processors, random access memory (RAM), and a non-transitory computer-readable storage medium storing instructions for execution by the one or more processors. The computing device receives first data and classifies the first data using a neural network that includes at least one quantized layer. The classifying includes reading values from the random access memory for a set of weights of the at least one quantized layer of the neural network using first read parameters corresponding to a first error rate.