Abstract: An example of the present disclosure provides a stereo camera assembly of an object tracking system. The stereo camera assembly comprises a wide-angle lens camera mounted on a mounting structure and a telephoto lens camera mounted on the mounting structure such that a field of view of the telephoto lens camera is at least partially encompassed by a field of view of the wide-angle lens camera.

Abstract: A method of decoding motion information according to an embodiment includes: determining a base motion vector of a current block; determining a primary differential motion vector for the current block based on information obtained from a bitstream from among one or more primary differential motion vector candidates classified according to a disparity distance and a disparity direction; and determining a motion vector of the current block by applying the primary differential motion vector to the base motion vector.

Abstract: An optical display system has an optical waveguide combiner and one or more cameras. The one or more camera(s) is optically coupled to the optical waveguide combiner and have a field of view of at least one real object and at least one virtual object displayable by the optical display system. The one or more camera(s), which may be for example wafer level waveguide camera(s), may be disposed outside the usable field of view of an output coupler. The one or more camera(s) may be self-calibrated electronically using images captured by the cameras of one or more virtual object(s) displayable by the optical display system. AR/VR/MR registration of devices and/or displayed virtual objects with real objects may be implemented using the images captured by the one or more camera(s) of the displayed virtual objects and real world objects. Real object distance and/or spatial location relative to the optical waveguide combiners may be determined or estimated from the captured images.

Abstract: A bowl-shaped photographic stage and photographic system is provided that produces consistent diffused lighting of an object or subject that is virtually shadow free for obtaining rotational views of the object in a time efficient manner. The bowl-shaped photographic stage may be used with a camera array, or a single camera may be moved around the circumference of the photographic stage to obtain a series of images needed to form a rotational view of an object or subject. Alternatively, the bowl-shaped photographic stage may be rotated to pass by a single fixed camera to obtain a series of images needed to form a rotational view of an object or subject.

Abstract: A method of decoding image data is provided. The method may include generating a dequantized block of an image based on a coded bitstream; determining whether to use one from among an implicit method and an explicit method for selecting a hybrid transform kernel from among one or more hybrid transform kernel that are available for decoding the dequantized block, wherein the one or more hybrid transform kernel are available for decoding the dequantized block based on associations between prediction modes and sizes of blocks; selecting, by using the one from among the implicit method and the explicit method, the hybrid transform kernel from among the one or more hybrid transform kernel; and performing inverse transform coding of the dequantized block based on the selected hybrid transform kernel.

Abstract: A video decoding method, a video encoding method, and related apparatuses. The video decoding method includes: determining a current video frame; obtaining, from video frames that have been decoded, a first quantity of blocks of a first size and a second quantity of blocks of a second size in a reference frame associated with the current video frame, the first size being less than the second size; determining, according to a relationship between the first quantity and the second quantity, a target resolution used for decoding the current video frame; and decoding the current video frame by using the target resolution. In this application, the technical problem of the relatively low video encoding and decoding efficiency caused by complex processing operations in the related art is resolved.

Abstract: A method, computer program, and computer system is provided for video coding. Video data comprising a reference frame and residual blocks is received. Transform coefficients associated with the residual blocks are identified. The video data corresponding to the one or more residual blocks is encoded based on an extended dynamic range associated with the transform coefficients.

Abstract: An electronic device may provide visual content at a virtual image distance that is farther from a user than the physical distance of the device from the user. A display in the device may have a transmissive spatial light modulator and beam steering device that are illuminated by a plane wave illumination system to provide computer-generated hologram images, may have a waveguide-based system that ensures that image content is presented at a desired virtual image distance, or may be a light-field display. The display may be used to display a left image in a left eye box and a right image in a right eye box. When viewed from the eye boxes, the left and right images fuse and are visible at a virtual image distance that is farther from the user than the distance physically separating the eye boxes from the display.

Abstract: A vehicle system includes a display device that simulates a rear-facing mirror (e.g., rearview mirror). The display device displays a first video captured by a first camera to simulate the rear-facing mirror. The system detects a change in an orientation of the display device from a first orientation to a second orientation and, in response, causes the display device to display a second video captured by a second camera to maintain the simulation of the rearview mirror but from the second orientation. Alternatively, the system causes a corresponding change in the perspective of the first video being displayed on the display device thereby maintaining the effect of the rearview mirror.

Abstract: A method for video processing includes: refining motion vectors of a video block by using a motion refinement process; performing a prediction sample refinement for part of components of the video block using refined motion vectors of the video block; and performing a video processing on the video block based on the refined prediction sample.

Abstract: A structured light scanning method includes a light projector projecting a group of structured light to an object, an image capturing device capturing a group of images generated by the object reflecting the group of structured light, an image processor obtaining a pixel luminosity distribution of an image in the group of images, the image processor determining a reflection state of the image from the pixel luminosity distribution, the image processor determining whether to include the image in generating a depth map according to the reflection state, and the image processor decoding at least one image from the group of images to generate the depth map.

Abstract: The application relates to an intra block copy mode with dual tree partition. A method of video processing is disclosed. The method of video processing includes: determining, during a conversion between a current video block and a bitstream representation of the current video block, a block vector for the current video block; and performing, at least based on the block vector, the conversion, wherein when the current video block is coded with a coding mode using a reference block for prediction pointing to a same picture that the current video block is located in, and the current video block is a first type of block, the block vector is derived from at least one second type of block.

Abstract: A video decoding apparatus includes matrix reference pixel derivation circuitry that derives reference samples by using top neighboring samples and left neighboring samples of a current block, weight matrix derivation circuitry that derives a weight matrix, matrix prediction image derivation circuitry that derives a prediction image, and matrix prediction image interpolation circuitry that derives a predicted image by using the prediction image. A size index is derived according to a value of a target block width and a value of a target block height. A prediction size is derived using the size index. In a case that a first condition, that both the value of the transform block width and the value of the transform block height are equal to 4, is true, the size index is set equal to 0 and the prediction size is set equal to 4.

Abstract: Methods, systems, and devices for performing entropy coding for a palette escape symbol in palette mode coding and decoding are described. An example method for video processing includes performing a conversion between a video having one or more video regions including a current video block and a bitstream representation of the video, wherein the bitstream representation conforms to a format rule that the current video block is coded using a palette mode coding tool, wherein a binarization of an escape symbol for the current video block uses an exponential-Golomb (EG) code of order K, wherein K is a non-negative integer that is unequal to three, and wherein the palette mode coding tool represents the current video block using a palette of representative color values and wherein the escape symbol is used for a sample of the current video block coded without using the representative color values.

Abstract: A three-dimensional imaging apparatus includes: a housing having a first opening and a second opening; a first imaging device configured to collect a first set of image data, the first imaging device being mounted within the housing and having an optical axis through the first opening of the housing and a first field of view configured with respect to the optical axis; and a second imaging device configured to collect a second set of image data, the second imaging device being mounted within the housing and having a scanning plane through the second opening of the housing and a second field of view configured with respect to the scanning plane. The optical axis of the first imaging device and the scanning plane of the second imaging device form an angle. The first field of view and the second field of view do not overlap.

Abstract: A three-dimensional image device is provided. The three-dimensional image device includes a depth processor, a structured-light depth camera, and a TOF depth camera. The depth processor includes at least two input ports configured to receive first images, an input switch coupled to the at least two input ports, and a data processing engine coupled to the input switch. The at least two input ports include a first input port and a second input port, the first input port is coupled to the structured-light depth camera, and the second input port is coupled to the TOF depth camera.

Abstract: Individuals, business transactions, and business activities are monitored for actions and behaviors of the individuals during performance of establishment processes through video feeds captured by cameras, sensor data captured by sensors, and information captured by transaction systems. Transaction/activity information associated with transactions/activities being processed by a transaction system of the establishment or performed by individuals within the establishment are monitored. The actions, behaviors, transaction information, activity information, and establishment processes are correlated to process controls, policies, and procedures of the establishment and logged. Non-compliant actions, behaviors, transaction information, activity information, and/or transaction/activity thresholds generate real-time remedial actions, such as audits, training, and notifications.

Abstract: A system includes memory and at least one processor coupled to the memory. The processor processes a received bitstream to generate quantized data and control data. The process also generate decoded motion data based on a portion of the control data, fetches one or more reference blocks associated with a current prediction unit (PU) of a DPR based on the decoded motion data and generates refined motion data based on the decoded motion data and the one or more reference blocks. The processor further generates one or more inter-prediction blocks based on the refined motion data and the one or more reference blocks by performing a motion compensation operation.

Abstract: A method for video processing includes: refining motion vectors of a video block by using a motion refinement process; performing a prediction sample refinement for part of components of the video block using refined motion vectors of the video block; and performing a video processing on the video block based on the refined prediction sample.

Abstract: This disclosure relates to a transform kernel sharing in video encoding and decoding. For example, a method is disclosed for such transform kernel sharing. The method may include identifying a plurality of transform kernels, wherein each of the plurality of transform kernels comprises a set of basis vectors from low to high frequencies; N high-frequency basis vectors of two or more of the plurality of transform kernels are shared, N being a positive integer; and low-frequency basis vectors of the two or more of the plurality of the transform kernels other than the N high-frequency basis vectors are individualized. The method may further include extracting a data block from a video bitstream; selecting a transform kernel from the plurality of transform kernels based on information associated with the data block; and applying the transform kernel to at least a portion of the data block to generate a transformed block.