Abstract: Embodiments of the invention provide a camera array imaging architecture that computes depth maps for objects within a scene captured by the cameras, and use a near-field sub-array of cameras to compute depth to near-field objects and a far-field sub-array of cameras to compute depth to far-field objects. In particular, a baseline distance between cameras in the near-field subarray is less than a baseline distance between cameras in the far-field sub-array in order to increase the accuracy of the depth map. Some embodiments provide an illumination near-IR light source for use in computing depth maps.

Abstract: There are provided mechanisms for processing encoded image data. The method comprises receiving an encoded bitstream comprising parameter set information. The parameter set information may comprise a syntax indicator, a first coded portion comprising first coded sample information for a picture and a second coded portion comprising second coded sample information for the picture. The method further comprises, responsive to a first value of the syntax indicator, decoding the first coded sample information using a picture header syntax element from a picture header of the encoded bitstream. The method further comprises, responsive to the first value of the syntax indicator, decoding the second coded sample information using the picture header syntax element from the picture header of the encoded bitstream.

Abstract: A method of processing video data comprises obtaining a bitstream and locating intra random access pictures (IRAP) or Gradual Decoder Refresh (GDR) pictures among the encoded pictures in the bitstream. Locating the IRAP or GDR pictures may comprise obtaining, from a picture header Network Abstraction Layer (NAL) unit in the bitstream, a syntax element that indicates that a picture associated with the picture header NAL unit must be either an Intra Random Access Picture (IRAP) or a Gradual Decoder Refresh (GDR) picture. The picture header NAL unit contains syntax elements that apply to all slices of the picture associated with the picture header NAL unit.

Abstract: A video signal decoding apparatus comprising a processor, wherein the processor is configured to: parse a syntax element related to a secondary transform of a coding unit from a bitstream of a video signal when one or more preset conditions are satisfied; check whether or not the secondary transform is applied to a transform block included in the coding unit based on the parsed syntax element; obtain one or more inverse transform coefficients for a first sub-block by performing an inverse secondary transform based on one or more coefficients of the first sub-block which is one of one or more sub-blocks constituting the transform block when the secondary transform is applied to the transform block; and obtain a residual sample for the transform block by performing an inverse primary transform based on the one or more inverse transform coefficients.

Abstract: Embodiments of this disclosure provide a training method, an image encoding method, an image decoding method and apparatuses thereof. The image encoding apparatus includes: an image encoder configured to encode input image data to obtain a latent variable; a quantizer configured to perform quantizing processing on the latent variable according to a quantization step to generate a quantized latent variable; and an entropy encoder configured to perform entropy coding on the quantized latent variable by using an entropy model to form a bit stream.

Abstract: A motion estimation technique finds first and second candidate bi-directional motion vectors for a first region of an interpolated frame of video content by performing double ended vector motion estimation on the first region. One of these candidate bi-directional motion vectors is selected, and used to identify a remote region of the interpolated frame. This remote region is located at an off-set location from the first region, and is found based on an endpoint of the selected candidate bi-directional motion vector. A remote motion vector for the remote region of the interpolated frame is obtained, and one or more properties of this remote motion vector are used to bias a selection between the first and second candidate vectors.

Abstract: A method for decoding an encoded data stream representative of at least one image, which is divided into blocks. The decoding method includes, for a current block: evaluating a plurality of value hypotheses of at least one description element of the current block, by calculating a likelihood measurement per hypothesis; calculating a disparity in the likelihood measurements obtained; determining at least one parameter of a decoder based on the calculated disparity; decoding, using the determined decoder, complementary information for identifying at least one of the hypotheses; and identifying at least one of the hypotheses using the decoded complementary information and obtaining a value of the at least one description element for the current block, from the at least one identified hypothesis.

Abstract: A method, device, and computer-readable medium for decoding an encoded video bitstream using at least one processor, including obtaining a flag indicating that a conformance window is not used for reference picture resampling; based on the flag indicating that the conformance window is not used for the reference picture resampling, determining whether a resampling picture size is signaled; based on determining that the resampling picture size is signaled, determining a resampling ratio based on the resampling picture size; based on determining that the resampling picture size is not signaled, determining the resampling ratio based on an output picture size; and performing the reference picture resampling on a current picture using the resampling ratio.

Abstract: Provided is an image decoding method including determining a predicted quantization parameter of a current quantization group determined according to at least one of block split information and block size information, determining a difference quantization parameter of the current quantization group, determining a quantization parameter of the current quantization group, based on the predicted quantization parameter and the difference quantization parameter of the current quantization group, and inverse quantizing a current block included in the current quantization group, according to the quantization parameter of the current quantization group.

Abstract: A method includes obtaining a first motion vector of a motion compensation unit included in an affine code block. The method also includes determining a second motion vector based on the first motion vector, where a precision of the second motion vector matches a motion vector precision of a storage unit corresponding to the motion compensation unit. The method further includes determining a third motion vector based on the second motion vector, where there is a preset correspondence between the third motion vector and the second motion vector, and the third motion vector is used for subsequent encoding/decoding processing.

Abstract: A method for decoding a video bitstream. The bitstream comprises coded data for at least one picture, and each picture comprises at least one tile group. The method includes parsing a flag that specifies whether tile information for a coded picture is present in a parameter set or in a tile group header. The tile information indicates which tiles of the picture are included in a tile group. The method parses the tile information from either the parameter set or the tile group header based on the flag. The method obtains the decoded data of the coded picture based on the tile information.

Abstract: A decoder for decoding a data stream into which media data is coded has a mode switch configured to activate a low-complexity mode or a high-efficiency mode depending on the data stream, an entropy decoding engine configured to retrieve each symbol of a sequence of symbols by entropy decoding using a selected one of a plurality of entropy decoding schemes, a desymbolizer configured to desymbolize the sequence of symbols to obtain a sequence of syntax elements, a reconstructor configured to reconstruct the media data based on the sequence of syntax elements, selection depending on the activated low-complexity mode or the high-efficiency mode.

Abstract: Provided is a method for encoding parameter sets at slice level. The method includes: when there are one or more parameter sets, in which the coding tool parameters are identical to the coding tool parameters of a part of coding tools used for the current slice, in the existing parameter sets, encoding the identifiers of parameter sets into bit-stream of the current slice, wherein a parameter set contains common information of the coding tools used in the process of encoding/decoding slice(s). Correspondingly, also provided is a method for decoding parameter sets at slice level and a device for encoding and decoding parameter sets at slice level, which can make full use of the encoded parameter set information when the slice header refers to a plurality of parameter sets, implement flexible configuration of the coding tools used in the process of encoding/decoding slice(s) and reduce information redundancy.

Abstract: A method and device for encoding and a method and device for decoding a signal including encoded data representing an image sub-divided into blocks, and information representing a correction block and a residual block. For a current block of the image, a first pixel is encoded from a prediction value obtained for the first pixel from at least one pixel of a previously rebuilt block. The prediction is corrected using at least one value of a pixel of the correction block. At least one current pixel of the current block is encoded from a prediction value obtained for the current pixel from at least one previously corrected pixel of the current block. The prediction is corrected by using at least one value of a pixel of the correction block, delivering a prediction block for the current block. The residual block is computed from the current block and the predictive block.

Abstract: A method for partitioning of input vectors for coding is presented. The method comprises obtaining of an input vector. The input vector is segmented, in a non-recursive manner, into an integer number, NSEG, of input vector segments. A representation of a respective relative energy difference between parts of the input vector on each side of each boundary between the input vector segments is determined, in a recursive manner. The input vector segments and the representations of the relative energy differences are provided for individual coding. Partitioning units and computer programs for partitioning of input vectors for coding, as well as positional encoders, are presented.

Abstract: An imaging lens includes one or more lens elements configured to receive and focus light in a first wavelength range reflected off of one or more first objects onto an image plane, and to receive and focus light in a second wavelength range reflected off of one or more second objects onto the image plane. The imaging lens further includes an aperture stop and a filter positioned at the aperture stop. The filter includes a central region and an outer region surrounding the central region. The central region of the filter is characterized by a first transmission band in the first wavelength range and a second transmission band in the second wavelength range. The outer region of the filter is characterized by a third transmission band in the first wavelength range and substantially low transmittance values in the second wavelength range.

Abstract: Devices, systems and methods for temporal prediction of parameters in non-linear adaptive loop filtering are described. In an exemplary aspect, a method for visual media processing includes configuring, for a current video block, one or more parameters of a clipping operation that is part of a non-linear filtering operation; and performing, based on the one or more parameters, a conversion between the current video block and a bitstream representation of the current video block, wherein the one or more parameters is coded in accordance with a rule.

Abstract: An image decoding apparatus decodes a bit stream generated by coding an image and decodes coded data included in the bit stream and corresponding to a target block to be decoded in the image. The apparatus includes a first determining unit configured to determine whether the target block is prediction-coded or palette-coded; a second determining unit configured to determine whether or not a pixel in the target block is escape-coded if the first determining unit determines that the target block is palette-coded; and a first decoding unit configured to decode the target block by using a second quantization parameter different from a first quantization parameter if the second determining unit determines that the pixel is escape-coded. The first quantization parameter is used to decode the coded data in a case where the first determining unit determines that the target block is prediction-coded.

Abstract: According to one method, a method for decoding data using rate sorted entropy coding occurs at a video decoder implemented using at least one processor. The method comprises: receiving rate control information associated with a first bitstream; determining, using the rate control information, a maximum amount of bits available for a next symbol in the first bitstream; determining, using a symbol probability model and a first deterministic algorithm, an amount of bits for a least probable value of the next symbol; and determining that the next symbol is included in the first bitstream if the amount of bits for the least probable value of the next symbol is less than or equal to the maximum amount of bits available for the first bitstream.

Abstract: Disclosed herein are a method and apparatus for measuring video quality based on a perceptually sensitive region. The quality of video may be measured based on a perceptually sensitive region and a change in the perceptually sensitive region. The perceptually sensitive region includes a spatial perceptually sensitive region, a temporal perceptually sensitive region, and a spatio-temporal perceptually sensitive region. Perceptual weights are applied to a detected perceptually sensitive region and a change in the detected perceptually sensitive region. Distortion is calculated based on the perceptually sensitive region and the change in the perceptually sensitive region, and a result of quality measurement for a video is generated based on the calculated distortion.