Abstract: A superpixel sampling network utilizes a neural network coupled to a differentiable simple linear iterative clustering component to determine pixel-superpixel associations from a set of pixel features output by the neural network. The superpixel sampling network computes updated superpixel centers and final pixel-superpixel associations over a number of iterations.

Abstract: The present invention facilitates efficient and effective utilization of storage management features. In one embodiment, a system comprises: a storage component, a memory controller, and a communication link. The storage component stores information. The memory controller controls the storage component. The communication link communicatively couples the storage component and the memory controller. In one embodiment, the communication link communicates storage system management information between the memory storage component and memory controller, and communication of the storage system management information does not interfere with command/address information communication and data information communication.

Abstract: A method, computer readable medium, and system are disclosed for sequential multi-tasking to generate coordinates of landmarks within images. The landmark locations may be identified on an image of a human face and used for emotion recognition, face identity verification, eye gaze tracking, pose estimation, etc. A neural network model processes input image data to generate pixel-level likelihood estimates for landmarks in the input image data and a soft-argmax function computes predicted coordinates of each landmark based on the pixel-level likelihood estimates.

Abstract: A method, computer readable medium, and system are disclosed to generate coordinates of landmarks within images. The landmark locations may be identified on an image of a human face and used for emotion recognition, face identity verification, eye gaze tracking, pose estimation, etc. A transform is applied to input image data to produce transformed input image data. The transform is also applied to predicted coordinates for landmarks of the input image data to produce transformed predicted coordinates. A neural network model processes the transformed input image data to generate additional landmarks of the transformed input image data and additional predicted coordinates for each one of the additional landmarks. Parameters of the neural network model are updated to reduce differences between the transformed predicted coordinates and the additional predicted coordinates.

Abstract: A distributed deep neural net (DNN) utilizing a distributed, tile-based architecture includes multiple chips, each with a central processing element, a global memory buffer, and a plurality of additional processing elements. Each additional processing element includes a weight buffer, an activation buffer, and vector multiply-accumulate units to combine, in parallel, the weight values and the activation values using stationary data flows.

Abstract: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.

Abstract: The introduced method and system use a 4-dimensional (4D) light field as a background of a scene, instead of 2D background image. Realizing computing a light field takes tremendous amounts of processing power, data storage and time (even with the currently available hardware), the introduced method and system compute and store the light field before rendering a scene. To reduce the time storing and accessing the light field during the rendering process, the introduced method and system also uses a modified video codec to compress and decompress the light field as 2D images.

Abstract: Various types of systems or technologies can be used to collect data in a 3D space. For example, LiDAR (light detection and ranging) and RADAR (radio detection and ranging) systems are commonly used to generate point cloud data for 3D space around vehicles, for such functions as localization, mapping, and tracking. This disclosure provides improvements for processing the point cloud data that has been collected. The processing improvements include analyzing point cloud data using trajectory equations, depth maps, and texture maps. The processing improvements also include representing the point cloud data by a two dimensional depth map or a texture map and using the depth map or texture map to provide object motion, obstacle detection, freespace detection, and landmark detection for an area surrounding a vehicle.

Abstract: Video interpolation is used to predict one or more intermediate frames at timesteps defined between two consecutive frames. A first neural network model approximates optical flow data defining motion between the two consecutive frames. A second neural network model refines the optical flow data and predicts visibility maps for each timestep. The two consecutive frames are warped according to the refined optical flow data for each timestep to produce pairs of warped frames for each timestep. The second neural network model then fuses the pair of warped frames based on the visibility maps to produce the intermediate frame for each timestep. Artifacts caused by motion boundaries and occlusions are reduced in the predicted intermediate frames.

Abstract: A system and method for solving linear complementarity problems for rigid body simulation is disclosed. The method includes determining a plurality of modified effective masses for a plurality of contacts between a plurality of bodies, wherein each modified effective mass term is based on a corresponding number of contacts. A plurality of relative velocities is determined based on the plurality of body velocities determined from a last iteration. A plurality of impulse corrections is determined based on the plurality of modified effective masses and the plurality of relative velocities. A plurality of updated impulses is determined based on the impulse corrections. The plurality of updated impulses is applied to the plurality of bodies based on a plurality of original masses of the bodies, body velocities determined from the last iteration, to determine a plurality of updated velocities of the plurality of bodies.

Abstract: The present disclosure provides methods, systems, and computer program products that use deep learning models to classify candidate mutations detected in sequencing data, particularly suboptimal sequencing data. The methods, systems, and programs provide for increased efficiency, accuracy, and speed in identifying mutations from a wide range of sequencing data.

Abstract: Multiprocessor clusters in a virtualized environment conventionally fail to provide memory access security, which is frequently a requirement for efficient utilization in multi-client settings. Without adequate access security, a malicious process may access what might be confidential data that belongs to a different client sharing the multiprocessor cluster. Furthermore, an inadvertent programming error in the code for one client process may accidentally corrupt data that belongs to the different client. Neither scenario is acceptable. Embodiments of the present disclosure provide access security by enabling each processing node within a multiprocessor cluster to virtualize and manage local memory access and only process access requests possessing proper access credentials. In this way, different applications executing on a multiprocessor cluster may be isolated from each other while advantageously sharing the hardware resources of the multiprocessor cluster.

Abstract: System and methods for detecting blockages in images are described. A method may include receiving a plurality of images captured by a camera installed on a vehicle. The method may include identifying one or more candidate blocked regions in the plurality of images. Each of the candidate blocked regions may contain image data caused by blockages in the camera's field-of-view. The method may further include assigning blockage scores to the one or more candidate blocked regions based on region-associations among the one or more candidate blocked regions in the plurality of images. In response to a determination that one of the blockage scores is above a predetermined blockage threshold, the method may include transmitting a blockage alarm signal to the vehicle.

Abstract: Various types of systems or technologies can be used to collect data in a 3D space. For example, LiDAR (light detection and ranging) and RADAR (radio detection and ranging) systems are commonly used to generate point cloud data for 3D space around vehicles, for such functions as localization, mapping, and tracking. This disclosure provides improvements for processing the point cloud data that has been collected. The processing improvements include using a three dimensional polar depth map to assist in performing nearest neighbor analysis on point cloud data for object detection, trajectory detection, freespace detection, obstacle detection, landmark detection, and providing other geometric space parameters.

Abstract: A spatial linear propagation network (SLPN) system learns the affinity matrix for vision tasks. An affinity matrix is a generic matrix that defines the similarity of two points in space. The SLPN system is trained for a particular computer vision task and refines an input map (i.e., affinity matrix) that indicates pixels the share a particular property (e.g., color, object, texture, shape, etc.). Inputs to the SLPN system are input data (e.g., pixel values for an image) and the input map corresponding to the input data to be propagated. The input data is processed to produce task-specific affinity values (guidance data). The task-specific affinity values are applied to values in the input map, with at least two weighted values from each column contributing to a value in the refined map data for the adjacent column.

Abstract: A computer system comprising: a graphics processor, a display controller comprising a display-local frame buffer, a display device, and a memory. The memory stores instructions, that when executed by the computer system, perform a method of entering a power management state. The method comprises detecting that the computer system is idle and optional proximity detector for determining if a user is present in front of the system. With the computer system idle, and the user in proximity of the system, the display-local frame buffer is activated. Display information transmitted by the graphics processor is stored in the display-local frame buffer. Initially a power reduction state is initiated for the graphics subsystem including the graphics processor, and the display device is placed in a self-refresh state with the display self-refreshing from information stored in the local frame buffer.

Abstract: The present invention facilitates efficient and effective utilization of unified virtual addresses across multiple components. In one exemplary implementation, an address allocation process comprises: establishing space for managed pointers across a plurality of memories, including allocating one of the managed pointers with a first portion of memory associated with a first one of a plurality of processors; and performing a process of automatically managing accesses to the managed pointers across the plurality of processors and corresponding memories. The automated management can include ensuring consistent information associated with the managed pointers is copied from the first portion of memory to a second portion of memory associated with a second one of the plurality of processors based upon initiation of an accesses to the managed pointers from the second one of the plurality of processors.

Abstract: When a computer image is generated from a real-world scene having a semi-reflective surface (e.g. window), the computer image will create, at the semi-reflective surface from the viewpoint of the camera, both a reflection of a scene in front of the semi-reflective surface and a transmission of a scene located behind the semi-reflective surface. Similar to a person viewing the real-world scene from different locations, angles, etc., the reflection and transmission may change, and also move relative to each other, as the viewpoint of the camera changes. Unfortunately, the dynamic nature of the reflection and transmission negatively impacts the performance of many computer applications, but performance can generally be improved if the reflection and transmission are separated. The present disclosure uses deep learning to separate reflection and transmission at a semi-reflective surface of a computer image generated from a real-world scene.

Abstract: A memory management unit responds to an invalidate by class command by identifying a marker for a class of cache entries that the invalidate by class command is meant to invalidate. The memory management unit stores the active marker as a retired marker and then sets the active marker to the next available marker. Thereafter, the memory management sends an acknowledgement signal (e.g., to the operating system) while invalidating the cache entries having the class and the retired marker in the background. By correlating markers with classes of cache entries, the memory management can more quickly respond to class invalidation requests.

Abstract: The present invention provides a printed circuit board and a layout method thereof and an electronic equipment. On the printed circuit board is arranged a first processor chip and a second processor chip, wherein the first processor chip is arranged on a first surface of the printed circuit board; the second processor chip is arranged on a second surface of the printed circuit board; and a first through-hole is disposed on the printed circuit board, part of pins of the first processor chip being connected to part of pins of the second processor chip via the first through-hole.