Abstract: The quality of a frame sequence is enhanced by a booster engine collaborating with a first stage circuit. The first stage circuit adjusts the quality degradation of the frame sequence when a condition in constrained resources is detected. The quality degradation includes at least one of uneven resolution and uneven frame per second (FPS). The booster engine receives the frame sequence from the first stage circuit, and generates an enhanced frame sequence based on the frame sequence for transmission to a second stage circuit.

Abstract: An annunciation method includes the steps of obtaining first position information as position information of a place where a first object is located, obtaining second position information as position information of a place where a second object is located, obtaining third position information as position information of a place where a third object is located, setting the first object and the second object as a first group when a distance between the first object and the second object calculated based on the first position information and the second position information is smaller than or equal to a first threshold value, obtaining fourth position information representing a position of the first group, and performing annunciation when a distance between the third object and the first group calculated based on the third position information and the fourth position information is smaller than a second threshold value.

Abstract: Rendering an avatar may include determining an expression to be represented by an avatar, obtaining a blood texture map associated with the expression, wherein the blood texture map represents an offset of coloration from an albedo map for the expression, and rendering the avatar utilizing the blood texture map.

Abstract: Various implementations track an eye using both camera images and light sensor data, e.g., from a photosensitive surface or set of photodetectors. The camera need not capture images at a high capture rate since the light sensor data captured from the light sensor provides information about the eye during the time periods between camera frames. An eye tracking device may thus provide eye tracking with high temporal resolution using less power and resources and prior devices. The eye tracking device includes a lens (e.g., a diffractive optical element (DOE)) that splits received light onto the camera and light sensor. The camera and light sensor may be aligned, e.g., co-centered. Using such a lens to provide light to an aligned camera and light sensor facilitates tracking the eye characteristics by reducing the need for matching the data and/or accounting for multiple environmental light sources.

Abstract: A three-dimensional data encoding method includes: assigning three-dimensional points to one of layers, based on items of geometry information of the three-dimensional points; searching three-dimensional points surrounding a current three-dimensional point to be encoded, to select, from the three-dimensional points, a three-dimensional point to be referred to when a predicted value of attribute information of the current three-dimensional point is calculated, the current three-dimensional point belonging to a first layer among the layers; and calculating the predicted value of the attribute information of the current three-dimensional point using the three-dimensional point selected. In the searching of the three-dimensional points, a search range for a same layer as the current three-dimensional point is different from a search range for a layer higher than the first layer.

Abstract: The present disclosure provides an electronic system with defect identification function and a method of qualifying a photoresist pattern formed using a lithography process. The electronic system includes an inspection apparatus and a processor associated with the inspection apparatus. The inspection apparatus is used for acquiring at least one image of the specimen on which a photoresist pattern is formed using a lithography process. The processor is configured to automatically apply machine learning processes implemented through one or more neural networks to identify at least one defect present in the photoresist pattern.

Abstract: Items are identified in a waste stream for purposes of recycling, using deterministic and/or probabilistic techniques. Imagery of the waste stream from multiple viewpoints permit creation of a 3D depth draped image representation, from which one or more 2D planes can be synthesized. Phase-coherent patches of recoverable encoded data can be identified from among soiled and crumpled object surfaces, and used in combination to recover object identification information. Recognition of certain items can trigger further image processing that is specific to such items. (Detection of a catsup bottle, for example, can trigger image analysis to discern the presence of catsup residue.) Information about recognized objects can be provided to external data customers, e.g., to track grey market diversion of particular products into unlicensed territories. These and other features and advantages, which can be used alone or in combination, are detailed herein.

Abstract: According to an embodiment, a method for generating a digital data set for fabricating a physical dental bleaching tray useable to deliver an bleaching agent is disclosed. The method includes obtaining a three-dimensional digital representation of a patient's dentition including teeth and gingiva; segmenting two or more teeth into individual tooth; identifying a facial surface of at least one of the segmented tooth; defining a facial surface portion including a surface area that is at least partly bound by a virtual boundary that is non-interfacing with the gingiva; generating a modified three-dimensional digital representation using the defined facial surface portion; and generating, based on the modified three-dimensional digital representation, the digital data set configured to be used in fabricating the physical dental bleaching tray.

Abstract: A computer apparatus and method for identifying and visualizing tumors in a histological image and measuring a tumor margin are provided. A CNN is used to classify pixels in the image according to whether they are determined to relate to nontumorous tissue, or one or more classes for tumorous tissue. Segmentation is carried out based on the CNN results to generate a mask that marks areas occupied by individual tumors. Summary statistics for each tumor are computed and supplied to a filter which edits the segmentation mask by filtering out tumors deemed to be insignificant. Optionally, the tumors that pass the filter may be ranked according to the summary statistics, for example in order of clinical relevance or by a sensible order of review for a pathologist. A visualization application can then display the histological image having regard to the segmentation mask, summary statistics and/or ranking. Tumor masses extracted by resection are painted with an ink to highlight its surface region.

Abstract: A system for producing a depth map can include a processor and a memory. The memory can store a neural network. The neural network can include an encoding portion module, a multi-frame feature matching portion module, and a decoding portion module. The encoding portion module can include instructions that, when executed by the processor, cause the processor to encode an image to produce single-frame features. The multi-frame feature matching portion module can include instructions that, when executed by the processor, cause the processor to process the single-frame features to produce information. The decoding portion module can include instructions that, when executed by the processor, cause the processor to decode the information to produce the depth map. A first training dataset, used to train the multi-frame feature matching portion module, can be different from a second training dataset used to train the encoding portion module and the decoding portion module.

Abstract: A method for encoding and decoding, an encoder and decoder for a point cloud. The method for encoding a point cloud to generate a bitstream of compressed point cloud data, in which the point cloud's geometry is represented by an octree-based structure with a plurality of nodes having parent-child relationships by recursively splitting a volumetric space containing the point cloud into sub-volumes each associated with a node of the octree-based structure, includes: determining an occupancy pattern for a parent node based on the occupancy of its child nodes; determining a planar context information for at least one of the child nodes; and entropy encoding/decoding the occupancy pattern parent node based on the determined planar context information to produce encoded/decoded data for the bitstream.

Abstract: At least one embodiment relates to a method comprising encoding a projection mode associated with an image region of a first depth image, said projection mode indicating if said image region stores either the minimum or the maximum depth value of at least one orthogonally projected 3D point of the point cloud along a same projection direction; and encoding said depth minimum and maximum depth values as a function of said projection mode.

Abstract: Systems and methods for performing semantic segmentation of three-dimensional data are provided. In one example embodiment, a computing system can be configured to obtain sensor data including three-dimensional data associated with an environment. The three-dimensional data can include a plurality of points and can be associated with one or more times. The computing system can be configured to determine data indicative of a two-dimensional voxel representation associated with the environment based at least in part on the three-dimensional data. The computing system can be configured to determine a classification for each point of the plurality of points within the three-dimensional data based at least in part on the two-dimensional voxel representation associated with the environment and a machine-learned semantic segmentation model. The computing system can be configured to initiate one or more actions based at least in part on the per-point classifications.

Abstract: Provided are a vehicle monitoring method and a vehicle monitoring system. The vehicle monitoring method includes that: a polarization angle of polarized light in a sky image reflected by a vehicle window in a monitoring scenario is calculated, and a light-filtering polarization angle is calculated according to the polarization angle of the polarized light in the sky image reflected by the vehicle window, where the polarized light in the sky image is formed by scattered sunlight in a sky region corresponding to the sky image; the polarized light in the sky image reflected by the vehicle window in the monitoring scenario is filtered out according to the light-filtering polarization angle; and the monitoring scenario is imaged to form a monitoring image.

Abstract: A method and apparatus for vascular assessment are disclosed. The apparatus, in some embodiments, receives, from a medical imaging device, a medical image of a coronary vessel tree of a subject and calculates a plurality of geometric measurements associated with individual portions of a vascular segment of the coronary vessel tree. The apparatus also determines a plurality of resistances associated with the plurality of geometric measurements associated with the individual portions of the vascular segment and determines a plurality of pressure drops across the individual portions of the vascular segment based on the determined resistances and a calculated or estimated blood flow. The apparatus further calculates based on the plurality of pressure drops, a functional index indicative of a presence or an absence of a stenosis within the vascular segment.

Abstract: Methods and systems are described for registering a sports field to a video. Video of a live event may feature participants at a venue. A template of the venue, including virtual markings that represent real markings on the venue, may be obtained. A homographic transformation between an image plane and a ground plane may be determined by matching virtual markings to corresponding real markings captured in at least one frame of the video. The determined homographic transformation may be used in the automated analysis of sports statistics and in improving inserted annotations and visualizations.

Abstract: A video localization system localizes actions in videos based on a classification model and an actionness model. The classification model is trained to make predictions of which segments of a video depict an action and to classify the actions in the segments. The actionness model predicts whether any action is occurring in each segment, rather than predicting a particular type of action. This reduces the likelihood that the video localization system over-relies on contextual information in localizing actions in video. Furthermore, the classification model and the actionness model are trained based on weakly-labeled data, thereby reducing the cost and time required to generate training data for the video localization system.

Abstract: A method and system for processing a purchase based on image recognition in a video stream being presented by a computing system. A method includes receiving a first user-input defining a first user-request to pause presentation of the video stream, and, responsive to the first user-input, pausing by the computing system the presentation of the video stream at a video frame. Further, the method includes detecting based on computer-vision analysis of the video frame, at least one object depicted by the video frame. Additionally, the method includes correlating the detected object with at least one purchasable item and presenting a prompt for purchase of the at least one purchasable item. Also, the method includes receiving a second user-input requesting to purchase a given one of the at least one purchasable item and processing, responsive to receiving the second user-input, a purchase of the given purchasable item for the user.

Abstract: A method and apparatus for coding information of a point cloud may be performed by at least one processor and comprises: obtaining the point cloud including a set of points in a three-dimensional space; partitioning the point cloud into a tree structure comprising a plurality of nodes at different depths; encoding geometry information of the nodes; and encoding attribute information of the nodes before the entire point cloud is partitioned.

Abstract: A computer-implemented method for transforming a neural radiance field model is described. A plurality of inputs are provided to a neural radiance field (NeRF) model that represents a 3-dimensional space having a subject, wherein each input of the plurality of inputs includes a location and a view direction and corresponds to respective colors of voxels that represent the 3-dimensional space. A spectral analysis is performed on a plurality of outputs of the NeRF model based on the plurality of inputs, wherein the plurality of outputs include the respective colors of the voxels. Frequency components of the spectral analysis that represent colors for at least some of the voxels are extracted. A sparse volume data structure that represents the 3-dimensional space and the respective colors for the at least some of the voxels is generated.