Abstract: A picture encoding apparatus configured to hierarchically partition a block of picture data into sub-blocks; determine that a sub-block being coded belongs to an unequally-sized partitioned block; prepare a list of neighboring blocks for the sub-block of the unequally-sized partitioned block based on a size of the sub-block of the unequally-sized partitioned block and a partitioning type of at least one neighboring block of the unequally-sized partitioned block; and derive a context model that is used to encode split information of the sub-block of the unequally-sized partitioned block into a bit stream based on the prepared list of neighboring blocks.

Abstract: A machine-learned image compression model includes a first encoder configured to generate a first image code based at least in part on first image data. The first encoder includes a first series of convolutional layers configured to generate a first series of respective feature maps based at least in part on the first image. A second encoder is configured to generate a second image code based at least in part on second image data and includes a second series of convolutional layers configured to generate a second series of respective feature maps based at least in part on the second image and disparity-warped feature data. Respective parametric skip functions associated convolutional layers of the second series are configured to generate disparity-warped feature data based at least in part on disparity associated with the first series of respective feature maps and the second series of respective feature maps.

Abstract: An example device for coding video data determines a first reference block in a first reference picture for a first block of a current picture. Based on the first reference picture being a different size than the current picture, the device codes the first block with a first inter-coding tool of a first set of inter-coding tools, wherein a first particular tool of a plurality of inter-coding tools is disabled. The device determines a second reference block in a second reference picture for a second block of the current picture. Based on the second reference picture being the same size as the current picture, the device codes the second block with a second inter-coding tool of a second set of inter-coding tools, wherein the first particular tool is enabled.

Abstract: The present invention is related to processing a video signal. A method for decoding a video according to the present invention may comprise generating a prediction block of a current block by performing intra prediction, deriving at least one sample position based parameter based on a position of a first prediction sample in the prediction block, and obtaining a second prediction sample by weighted predicting the first prediction sample based on the at least one sample position based parameter. According to the present invention, encoding/decoding efficiency of a video signal can be improved since intra prediction is performed more accurately.

Abstract: Innovations in range asymmetric number system (“RANS”) coding and decoding are described herein. Some of the innovations relate to hardware implementations of RANS decoding that organize operations in two phases, which can improve the computational efficiency of RANS decoding. Other innovations relate to adapting RANS encoding/decoding for different distributions or patterns of values for symbols. For example, RANS encoding/decoding can adapt by switching a default symbol width (the number of bits per symbol), adjusting symbol width on a fragment-by-fragment basis for different fragments of symbols, switching between different static probability models on a fragment-by-fragment basis for different fragments of symbols, and/or selectively flushing (or retaining) the state of a RANS decoder on a fragment-by-fragment basis for different fragments of symbols. In many cases, such innovations can improve compression efficiency while also providing computationally efficient performance.

Abstract: A method of encoding a first image in a plurality of images of input video data, wherein the first image is divided into a plurality of pixel blocks comprises, for a current block of the first image: determining a motion speed for the current block with respect to a reference block correlated to the current block in a second image of the plurality of images, wherein the second image is distinct from the first image and was previously encoded according to an image encoding sequence for encoding the images of the plurality of images; determining an interpolation filter based on the motion speed; and using the interpolation filter for calculating fractional pixel values in the second image for a temporal prediction of pixels of the current block based on the reference block of the second image.

Abstract: Encoding and streaming methods and apparatus are described. Objects in negative parallax in frame pairs, e.g., pairs of left and right eye images forming a stereoscopic image, are identified. An amount of negative parallax reduction implemented depends, in some embodiments, on the data rate being used for encoding and/or the amount of negative parallax detected in the frame pair to be encoded. The lower the supported data rate the greater the reduction in negative parallax in some embodiments. In some, but not all, embodiments objects in positive parallax, e.g., objects appearing to go into the page, are not subject to parallax reduction. When a lowest supported data rate is used mono encoding is used and parallax reduction steps are skipped. The same frame pair is encoded multiple times at different data rates. Different amounts of negative parallax reduction are performed for at least some of the different supported data rates.

Abstract: Systems and methods for producing a traceable measurement of a component are provided. One or more augmented reality (AR) graphical elements, indicative of a measurement to be performed on the component using a local measurement instrument, are generated. The AR graphical elements are rendered via an AR device. One or more measurement values, associated with the measurement as performed on the component using the local measurement instrument, are obtained. An augmented image comprising a representation of the component, a representation of the local measurement instrument obtaining the measurement values, and a representation of the AR graphical elements is acquired. The measurement values are stored in association with the augmented image.

Abstract: The invention includes systems and methods to provide a non-intrusive 360 view without a camera at the viewpoint. The invention processes video feeds from an array of cameras to track an object in the video feeds and generates an immersive media from the video feeds. The system identifies a primary object and tracks the primary object with an array of mounted sets of at least two cameras. Each of the sets including a camera directed at the object and another camera directed at a background of the object. The system then stitches the video feeds to generate the immersive media.

Abstract: Fixed-element, digital-optical measuring devices are disclosed, as are methods for using these devices. The measuring devices have two separate optical pathways with fixed elements that produce a stereo image. The optical pathways may include mirrors, prisms, beam splitters, and other such elements, or two digital sensors may be used. Image distance between stereo copies of a point of interest in the stereo image is measured digitally and converted to a physical distance from the measuring device. The conversion may be done with a non-trigonometric function, such as a function created using empirical data. In some cases, the function may be a function-of-functions that provides a calibration for a number of different lens focal lengths.

Abstract: The present disclosure provides systems and methods for performing adaptive resolution change during video encoding and decoding. The methods include: comparing resolutions of a target picture and a first reference picture; in response to the target picture and the first reference picture having different resolutions, resampling the first reference picture to generate a second reference picture; and encoding or decoding the target picture using the second reference picture.

Abstract: A method of determining “true” standstill in a vehicle. The method includes detecting an object outside of the vehicle via a camera, saving first data on the detected object in a memory, detecting the same object after a delay, saving, after the delay, second data on the detected object in a memory, analyzing, by a controller, the first and second data, and determining “true” standstill has occurred based on the analysis.

Abstract: A method, apparatus and computer program products are provided for capturing omnidirectional video with one or more cameras, streaming the video over a network, and rendering the video on a Head Mounted Display (HMD) and more specifically to a method, apparatus, and computer program product for improving the visual quality of viewport-based omnidirectional video streaming. One example method includes selecting a primary viewport, encoding a first representation that covers the primary viewport, and encoding a second representation that provides a gradual picture quality change from a background viewport to the primary viewport.

Abstract: A method of encoding video data into a video bitstream having a plurality of precincts. The method comprises generating a plurality of coding cost estimates for a current precinct by testing a corresponding candidate coefficient truncation level for the current precinct, each of the coding cost estimates being an over estimate of an encoded data size for coding the current precinct at the candidate truncation level and being determined using a most significant bit plane index, wherein each of the coding cost estimates is independent of a value of coefficient bits in the current precinct. The method includes selecting one of the candidate truncation levels according to the corresponding coding cost estimate and a budgeted coding cost for the current precinct, the budgeted coding cost representing an allowable size of encoding the precinct; and encoding the current precinct of video data into the video bitstream to generate the video bitstream.

Abstract: In one embodiment, an apparatus comprises processing circuitry to: receive, via a communication interface, a compressed video stream captured by a camera, wherein the compressed video stream comprises: a first compressed frame; and a second compressed frame, wherein the second compressed frame is compressed based at least in part on the first compressed frame, and wherein the second compressed frame comprises a plurality of motion vectors; decompress the first compressed frame into a first decompressed frame; perform pixel-domain object detection to detect an object at a first position in the first decompressed frame; and perform compressed-domain object detection to detect the object at a second position in the second compressed frame, wherein the object is detected at the second position in the second compressed frame based on: the first position of the object in the first decompressed frame; and the plurality of motion vectors from the second compressed frame.

Abstract: A motion vector determination employs template matching. At first, an initial motion vector is obtained. If the initial motion vector points to a position that is fractional, and thus, requires interpolation from the integer sample positions, the initial motion vector is rounded to a closest integer sample position. The rounded position is then used to define the search space for the template matching to define a refinement of the initial motion vector.

Abstract: A multi-camera system for multidimensional video capture is particularly useful for recording the movements of swimmers. The system includes a self-propelled mobile frame that is of sufficient size to surround a swimmer while he or she swims. The frame carries a number of equipment pods. Each equipment pod houses cameras, typically a pair of stereocameras, and may house additional sensors as well. Propulsion pods connect the frame to a pair of tracks, one of which is on each side of the frame, and propel the frame along the tracks. The frame may also support one or more booms that carry equipment pods with cameras and allow the system to capture video from additional angles. The frame carries transmission hardware allowing it to communicate video and other data to external receivers and communication devices in real time or near real time, and to receive data from external devices.

Abstract: A method of coding prediction information of a current block includes determining that the current block is to be coded according to an IntraBC mode (Intra Block Copy mode) and determining one or more block vector (BV) prediction candidates from one or more motion vectors (MVs) or BVs associated with neighboring blocks of the current block according to an advanced motion vector prediction (AMVP) mode or a Merge/Skip mode. The method further includes encoding or decoding a current BV based on a BV predictor selected from the one or more BV prediction candidates, where the current BV is for coding the current block according to the IntraBC mode.

Abstract: An apparatus including a video data decoder configured to decode an input video data stream, the video data decoder being responsive to a parameter value associated with the input video data stream, the parameter value indicating an encoding level selected from a plurality of encoding levels, each encoding level defining at least a maximum luminance picture size and a maximum luminance sample rate, the encoding level defining a first numerical component and a second numerical component, the second numerical component being a numerical value greater than or equal to zero, in which for encoding levels having a second numerical component of zero, the first numerical component increases monotonically with increasing maximum luminance picture size, and the second component varies with the maximum luminance sample rate; the parameter value being a numeric encoding of the encoding level.

Abstract: A 360-degree video data processing method performed by a 360-degree video reception apparatus, according to the present invention, comprises the steps of: receiving 360-degree video data for a plurality of views; deriving metadata and information on a packed picture; decoding the packed picture based on the information on the packed picture; deriving a specific packed region for a target view from the packed picture based on the metadata; deriving a projected picture of the target view based on the specific packed region and the metadata; and rendering the projected picture based on the metadata, wherein the metadata includes multiview region-wise packing information, and wherein the multiview region-wise packing information includes information about a packed region in the packed picture and information about the target view.