Abstract: A video encoder for encoding a video into a data stream using motion compensated prediction for inter predicted blocks, comprising a hypothesis number control, configured to control a number of prediction hypotheses of the inter predicted blocks within a predetermined portion of the video to meet a predetermined criterion.

Abstract: According to an aspect of an invention, a method for signaling reference pictures in video coding is disclosed. The method comprises: decoding a number of entries in a reference picture list syntax structure; decoding a number of reference index active minus one syntax in a slice header, if the number of entries is greater than one; and deriving an active variable by using the number of reference index active minus one syntax.

Abstract: A system and method for determining the performance of a video codec for real-time communication applications. A set of network conditions is used to simulate certain typical real-world network conditions. A coded video stream is transmitted from the transmitting end to the receiving end under these conditions. The end-to-end latency and received video fluency are measured along with a set of existing video quality measures by a video codec performance evaluation system including a network model and a video codec quality analyzer. The decodable frame ratio, latency and video fluency are used as the performance metrics for real-time communication video quality evaluation. The video codec performance evaluation system does not send any video data over a network when it determines the real-time communication quality of the video codec.

Abstract: An encoder calculates an indication to a previous reference picture having temporal identity of zero. The encoder creates a first set of indicators to the previous reference picture, to all reference pictures in a first reference picture set of the previous reference picture, and to all pictures following the previous reference picture in decoding order and precede the current picture in decoding order. The encoder sets a flag for picture order count cycle, when a long term reference picture (LTRP) has least significant bits (LSBs) of a picture order count, for which more than one picture in the first set share same value of the LSBs of picture order count as the LTRP. The decoder obtains LSB of a picture order count for a LTRP in a reference picture set of the current picture. The decoder concludes non-compliant bitstream based on indications provided by the flag.

Abstract: Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

Abstract: A method, performed by a decoding apparatus, of decoding motion information, including: obtaining change information indicating whether to change motion information of a neighboring block of a current block; based on the change information indicating to change the motion information, determining a prediction direction of the current block by changing a prediction direction of the neighboring block; based on the prediction direction of the neighboring block being a first uni-direction and the prediction direction of the current block being a second uni-direction or a bi-direction, selecting a reference picture of the second uni-direction of the current block from a second reference picture list; obtaining a motion vector of the second uni-direction of the current block; and reconstructing the current block using a reference block indicated by the motion vector of the second uni-direction of the current block.

Abstract: The present invention relates to a method and apparatus for processing a video signal, which can increase the accuracy of the motion vector prediction through motion vector scaling which takes a difference in the temporal distance between reference pictures into consideration. To this end, the present invention provides a video signal processing method and a video signal processing apparatus using the same, and the method comprises the steps of: scaling at least one neighboring partition motion vector for a motion vector prediction of the current partition; scaling the neighboring partition motion vector, which has been selected, when the reference picture of the neighboring partition motion vector is different from the reference picture of the current partition; acquiring a motion vector prediction value of the current partition using the scaled motion vector; and acquiring a motion vector of the current partition using the motion vector prediction value.

Abstract: A video decoding method executed by a video decoding apparatus according to the present document comprises the steps of: parsing a flag associated with weighted prediction from a bitstream; on the basis of the flag, parsing a prediction weighted table syntax from the bitstream; and on the basis of the prediction weighted table syntax, executing a weighted prediction on a current block in a current picture to reconstruct the current picture, wherein on the basis of the value of the flag being 1, the prediction weighted table syntax may be parsed from a picture header of the bitstream, and on the basis of the value of the flag being 0, the prediction weighted table syntax may be parsed from a slice header of the bitstream.

Abstract: Disclosed is a video signal processing method comprising the steps of: acquiring a merge index which indicates a candidate for prediction of a current block among a plurality of candidates for the prediction of the current block, which are included in a merge candidate list; acquiring motion information of the current block on the basis of motion information corresponding to the candidate indicated by the merge index; when the motion information of the current block includes a plurality of motion vectors corresponding to a list of different reference pictures, comparing picture order count (POC) differences between each of the reference pictures corresponding to the plurality of motion vectors and the current picture including the current block; correcting the plurality of motion vectors on the basis of a result of the comparison; and reconstructing the current block on the basis of the plurality of corrected motion vectors.

Abstract: A method of generating an image signal from a plurality of images of a scene performs iterations that comprise generating (505) predicted images for a candidate set of images from a set of (previously) included images. A set of selected images is selected (509) from the set of candidate images in response to a prediction quality. For each selected image a subset of pixels is determined (511) in response to pixel prediction qualities for the pixels of the image, and a set of partial images corresponding to the selected images is generated (513) by selecting (511) a subset of pixels. The selected image is deleted from the candidate set and the partial image is added to the included set. The approach may provide a low complexity and low resource selection of image data representing a scene.

Abstract: An encoder calculates an indication to a previous reference picture having temporal identity of zero. The encoder creates a first set of indicators to the previous reference picture, to all reference pictures in a first reference picture set of the previous reference picture, and to all pictures following the previous reference picture in decoding order and precede the current picture in decoding order. The encoder sets a flag for picture order count cycle, when a long term reference picture (LTRP) has least significant bits (LSBs) of a picture order count, for which more than one picture in the first set share same value of the LSBs of picture order count as the LTRP. The decoder obtains LSB of a picture order count for a LTRP in a reference picture set of the current picture. The decoder concludes non-compliant bitstream based on indications provided by the flag.

Abstract: Disclosed herein is a method for adaptive bidirectional optical flow estimation for inter-screen prediction compensation during video encoding. The method aims to reduce complexity and/or cost of bidirectional optical flow (BIO) at a pixel level or a subblock level.

Abstract: Disclosed herein is a method for adaptive bidirectional optical flow estimation for inter-screen prediction compensation during video encoding. The method aims to reduce complexity and/or cost of bidirectional optical flow (BIO) at a pixel level or a subblock level.

Abstract: Disclosed herein is a method for adaptive bidirectional optical flow estimation for inter-screen prediction compensation during video encoding. The method aims to reduce complexity and/or cost of bidirectional optical flow (BIO) at a pixel level or a subblock level.

Abstract: Disclosed herein is a method for adaptive bidirectional optical flow estimation for inter-screen prediction compensation during video encoding. The method aims to reduce complexity and/or cost of bidirectional optical flow (BIO) at a pixel level or a subblock level.

Abstract: A video decoding method performed by a video decoding device according to this document comprises the steps of: parsing prediction weighted table syntax from a bitstream; parsing information on the number of reference pictures in a reference picture list from the prediction weighted table syntax; deriving weights for weighted prediction on the basis of the information on the number of reference pictures; deriving prediction samples of a current block by performing weighted prediction for the current block on the basis of the weights; and reconstructing a current picture on the basis of the prediction samples, wherein the prediction weighted table syntax may be parsed from a picture header of the bitstream.

Abstract: A video decoding method executed by a video decoding apparatus according to the present document comprises the steps of: parsing a flag associated with weighted prediction from a bitstream; on the basis of the flag, parsing a prediction weighted table syntax from the bitstream; and on the basis of the prediction weighted table syntax, executing a weighted prediction on a current block in a current picture to reconstruct the current picture, wherein on the basis of the value of the flag being 1, the prediction weighted table syntax may be parsed from a picture header of the bitstream, and on the basis of the value of the flag being 0, the prediction weighted table syntax may be parsed from a slice header of the bitstream.

Abstract: A video encoder for encoding a video into a data stream using motion compensated prediction for inter predicted blocks, comprising a hypothesis number control, configured to control a number of prediction hypotheses of the inter predicted blocks within a predetermined portion of the video to meet a predetermined criterion.

Abstract: Disclosed is a video signal processing method comprising the steps of: acquiring a merge index which indicates a candidate for prediction of a current block among a plurality of candidates for the prediction of the current block, which are included in a merge candidate list; acquiring motion information of the current block on the basis of motion information corresponding to the candidate indicated by the merge index; when the motion information of the current block includes a plurality of motion vectors corresponding to a list of different reference pictures, comparing picture order count (POC) differences between each of the reference pictures corresponding to the plurality of motion vectors and the current picture including the current block; correcting the plurality of motion vectors on the basis of a result of the comparison; and reconstructing the current block on the basis of the plurality of corrected motion vectors.

Abstract: A system comprises a memory storage configured to store at least a portion of a frame of a video and a hardware motion estimation search processing unit configured to perform at least a portion of a motion estimation search for the video for a plurality of different block sizes. The hardware motion estimation search processing unit is configured to perform the motion estimation search using a plurality of source sub-blocks of a first block size to determine a first type of comparison evaluation values for the first block size. A combination of values included in the first type of comparison evaluation values is utilized to determine at least one second type of comparison evaluation values for a second block size, wherein the second block size is larger than the first block size.

Abstract: A data processing system for performing motion estimation in a sequence of frames having first and second frames each divided into respective sets of blocks of pixels, includes a vector generator configured to form motion vector candidates representing mappings of pixels between the first and second frames; and a vector processor configured to, for a search block of the first frame, identify a first motion vector candidate ending in a block of the second frame collocated with the search block and form an output vector for the search block which is substantially parallel to the first motion vector candidate and represents a mapping of pixels from the search block to the second frame.

Abstract: A terminal performs video estimation by dividing an image frame of a video into a plurality of prediction units, and dividing the plurality of prediction units into a first type of prediction units and a second type of prediction units. A motion vector of a prediction unit of the first type is then obtained according to a first search algorithm. A motion vector of a prediction unit of the second type is obtained according to a second search algorithm. The second search algorithm is different from the first search algorithm. Then sub-pixel motion estimation is performed on the image frame according to the motion vector of the prediction unit of the first type and the motion vector of the prediction unit of the second type to generate a motion estimate result.

Abstract: A method for encoding pictures within a groups of pictures using prediction, where a first reference picture from a group of pictures and a second reference pictures from the subsequent group of pictures are used in predicting pictures in the group of pictures associated with the first reference picture. A plurality of anchor pictures in the group of pictures associated with the first reference picture may be predicted using both the first and second reference pictures to ensure a smooth transition between different groups of pictures within a video frame.