Abstract: A method of visual media processing includes determining, for a conversion between a current video block of visual media data and a bitstream representation of the current video block, a buffer that stores reference samples for prediction in an intra block copy mode; for a sample spatially located at location of the current video block relative to an upper-left position of a coding tree unit including the current video block and having a block vector, computing a corresponding reference in the buffer at a reference location, wherein the reference location is determined using the block vector and the location; and upon determining that the reference location lies outside the buffer, re-computing the reference location based at least in part on a location of the current video block relative to the coding tree unit including the current video block.

Abstract: An image decoding method according to the present invention may include: a step for deriving merge candidates from neighboring blocks adjacent to a current block; a step for generating a first merge candidate list including the merge candidates; a step for decoding information for specifying any one of the merge candidates included in the first merge candidate list; and a step for deriving motion information about the current block from the merge candidate allocated with an index determined by the information. Here, when the number of the merge candidates included in the first merge candidate list is smaller than a predetermined value, merge candidates included in a second merge candidate list may be added to the first merge candidate list.

Abstract: A system for detecting defects in a contact lens material comprising: a camera having a lens and a digital image output for inspecting said lens suspended in saline solution, wherein said camera's digital image output includes only the image produced by light in a color spectrum corresponding to a portion of the spectrum of light produced by fluorescent emission of said lens material; a first Ultra violet light source to illuminate said lens and excite fluorescent emission therein; a first filter to filter the emitted light from the lens which is illuminated by Ultra violet light; and a computer having an associated memory, an input for accepting the digital image output from said camera, and an output representative of an analyzed digital image wherein said analyzed digital image includes visible indications of any imperfections detected in said lens material.

Abstract: A method for training a convolutional neural network to reconstruct an image. The method includes forming a common loss function basing on the left and right images (IL, IR), reconstructed left and right images (I?L, I?R), disparity maps (dL, dR), reconstructed disparity maps (d?L, d?R) for the left and right images (IL, IR) and the auxiliary images (I?L, I?R) and training the neural network based on the formed loss function.

Abstract: Methods and systems for light field image encoding and decoding are disclosed. According to some embodiments, scene metadata and input light field images associated with a scene are received. A first encoding operation is performed on the scene metadata and input light field images to generate reference images, reference disparity information, and an order of reference views. A second encoding operation is performed based on the reference images and reference disparity information to output light field encoded data. The light field encoded data includes the encoded reference images, the encoded reference disparity information, and the order of reference views. The light field encoded data is transmitted.

Abstract: A video decoding device includes a demultiplexer which demultiplexes a video bitstream including video data of an encoded slice, Supplemental-Enhancement-Information having first information indicating a leading picture in gradual refresh, and Supplemental-Enhancement-Information having second information indicating segments where a refresh has completed in a current picture; an extractor which extracts the second information from a message which is part of the demultiplexed Supplemental-Enhancement-Information; and a video decoder which decodes image data from the demultiplexed video bitstream by using at least inter prediction, wherein the video decoder starts decoding based on the leading picture in gradual refresh.

Abstract: In an implementation, a supplemental sequence parameter set (“SPS”) structure is provided that has its own network abstraction layer (“NAL”) unit type and allows transmission of layer-dependent parameters for non-base layers in an SVC environment. The supplemental SPS structure also may be used for view information in an MVC environment. In a general aspect, a structure is provided that includes (1) information (1410) from an SPS NAL unit, the information describing a parameter for use in decoding a first-layer encoding of a sequence of images, and (2) information (1420) from a supplemental SPS NAL unit having a different structure than the SPS NAL unit, and the information from the supplemental SPS NAL unit describing a parameter for use in decoding a second-layer encoding of the sequence of images. Associated methods and apparatuses are provided on the encoder and decoder sides, as well as for the signal.

Abstract: A vehicular control system includes a rear backup camera viewing at least rearward of the vehicle. With a trailer hitched to the vehicle, and based at least in part on image processing of captured image data during a backing-up maneuver, the image processor determines a distance between an axle of the trailer and the hitch of the vehicle and determines a trailer angle of the trailer hitched to the vehicle. During the backing-up maneuver of the trailer hitched to the vehicle, the vehicular control system determines a path of the trailer responsive to (i) a steering angle of the vehicle, (ii) the determined trailer angle of the trailer and (iii) the determined distance between the axle of the trailer and the hitch of the vehicle. The vehicular control system displays information to assist the driver in backing up the trailer hitched to the vehicle.

Abstract: A processor is configured to maintain, for encoding current values related to the transform coefficients a first line buffer and a second line buffer. The current values are arranged along a current scan-order anti-diagonal line. The first line buffer includes first values of a first scan-order anti-diagonal line. The second line buffer includes second values of a second scan-order anti-diagonal line. The processor is further configured to interleave the first values and the second values in a destination buffer; select, using the destination buffer, a probability distribution for coding a current value of the current values; entropy encode, in a compressed bitstream, the current value using the probability distribution; and replace, for coding values of an immediately subsequent scan-order anti-diagonal line to the current scan-order anti-diagonal line, one of the second line buffer or the first line buffer with the current scan-order anti-diagonal line.

Abstract: An image decoding apparatus (31) includes a CT information decoding unit (10) configured, in each coding tree, to decode a constraint flag indicating whether or not to constrain decoding a prediction unit, and a CU decoding unit (20) configured, in the coding tree, to decode a prediction unit in a coding node to be decoded first and to not decode a prediction unit in another coding node, in a case that the constraint flag indicates constraint of decoding the prediction unit. According to the present invention, it is possible to reduce a coding amount of PU and complexity of coding/decoding an image while maintaining a split with a high degree of freedom by CT split (QT split and BT split).

Abstract: An image decoding method according to the present invention comprises the steps of: deriving at least one merge candidate on the basis of at least one of a spatial neighboring block and a temporal neighboring block of a current block; generating a merge candidate list including the merge candidate; acquiring LX direction motion information of the current block, from a first merge candidate included in the merge candidate list; acquiring L(1-X) direction motion information of the current block, from a second merge candidate different from the first merge candidate; and performing inter-prediction on the basis of the LX direction motion information and the L(1-X) direction motion information.

Abstract: A method of coding implemented by a decoding device or an encoding device, comprising obtaining indication information for a luma position (cbWidth/2, cbHeight/2) of a current coding block, relative to a top-left luma sample postion (xCb, yCb) of the current coding block; setting a value of a luma intra prediction mode associated with the current coding block to a first default value, when the indication information indicates that a Matrix-based Intra Prediction (MIP) is applied for the luma component at the luma position (cbWidth/2, cbHeight/2), relative to the top-left luma sample postion (xCb, yCb) of the current coding block; and obtaining a value of a chroma intra prediction mode based on the value of the luma intra prediction mode of the current coding block.

Abstract: A monitor for displaying an image is disposed inside a front door of a car. The monitor is disposed at a position that does not overlap at least one of a front window and a front door window in a viewing direction of an occupant who sits in a front seat.

Abstract: A video encoding/decoding apparatus according to the present invention acquires motion vector refinement information, performs motion compensation on the basis of a motion vector of a current block, refines the motion vector of the current block using at least one or both of the motion vector refinement information and the output of the motion compensation, and performs motion compensation using the refined motion vector.

Abstract: The present disclosure relates to methods and apparatuses for encoding video data into a bitstream and for decoding video data received in a bitstream. A second control flag indicating whether or not to use multi-hypothesis prediction for intra and inter mode is generated and transmitted only conditionally, upon a determination whether or not separate merge list technique for subblock merge candidates is used. On the other hand, a decoder is capable of deciding usage of multi-hypothesis prediction for intra and inter mode and separate merge list technique for subblock merge candidates even though the second control flag is transmitted only conditionally.

Abstract: A decoder includes circuitry configured to receive a bitstream identify, in the bitstream, a current frame, wherein the current frame includes a first region and a third region, detect, in the bitstream, an indication that the first region is encoded according to a lossless encoding protocol, and decode the current frame, wherein decoding the current frame further comprises decoding the first region using a lossless decoding protocol corresponding to the lossless encoding protocol.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry. For example, the processing circuitry generates first reconstructed samples of a current block in a current frame. Further, the processing circuitry obtains reconstructed samples in a temporal source frame that is different from the current frame, and applies a filter to at least the reconstructed samples in the temporal source frame to generate offsets. Then, the processing circuitry combines the first reconstructed samples of the current block with the offsets to generate second reconstructed samples of the current block.

Abstract: A camera with a field of view of a shelf may acquire images of items on the shelf at subsequent times. An analysis of each image yields a set of estimated locations of the items on the shelf. Based on a working volume of the shelf, a subset of valid estimated locations of the items at the shelf may be determined. Thereafter, a count of the items on the shelf at a particular time may be determined using the subset of valid estimated item locations. By comparing the count of items at the shelf at two subsequent times, a change in quantity of the items on the shelf may be determined. Interaction data may be generated in response to detecting the change in quantity of items at the shelf.

Abstract: Disclosed are a method for processing a video signal by using an affine motion prediction and an apparatus thereof. A method for processing a video signal according to the present disclosure may include: adding, to an affine candidate list, an affine coded block coded in an affine prediction mode among neighbor blocks of a current block; obtaining a syntax element indicating a candidate used for the affine motion prediction of the current block in the affine candidate list; deriving a control point motion vector predictor of the current block based on an affine motion model of the candidate indicated by the syntax element; deriving a control point motion vector of the current block by adding a control point motion vector difference to the control point motion vector predictor; and generating a prediction block of the current block by using the control point motion vector of the current block.

Abstract: A device for decoding video data determine that a current block of video data is encoded in an affine linear weighted intra prediction (ALWIP) mode; derives, based on a set of left edge neighboring samples of the current block and a set of top edge neighboring samples of the current block, a subset of left edge samples and a subset of top edge samples; applies an affine model to the subset of left edge samples and the subset of top edge samples to generate an intermediate block of intermediate samples; filters the intermediate samples to generate a final prediction block; decodes the current block of video data based on the final prediction block.