Abstract: A decoder receives, from a bitstream, a first indication of a first bit depth for a sequence of frames, and a second indication of a second bit depth for a block in a frame of the sequence of frames, a residual block of samples of the second bit depth, and a prediction parameter. The decoder determines a first decoded block of samples of the second bit depth based on the second bit depth indicated by the second indication, the residual block of samples, and the prediction parameter. The decoder converts, based on a difference between the first bit depth and the second bit depth, the first decoded block of samples to a second decoded block of samples of the first bit depth based on the first decoded block of samples of the second bit depth and the first indication of the first bit depth for the sequence.

Abstract: In some embodiments, a decoder may receive, in a bit stream and for a block of samples, a residual and an indication of a downscaling. The decoder may determine reference samples for intra prediction of the block of samples. The decoder may generate, for an intra prediction mode, a prediction of the block of samples from the reference samples, The decoder may generate a first decoded block of samples based on: the prediction of the block of samples; and the residual. Based on the indication of the downscaling, the decoder may upscale the first decoded block of samples to a second decoded block of samples.

Abstract: A decoder receives, from a bitstream, an indication of a block vector, a residual of a current block, an indication of an affine transform, and affine transform parameters. The decoder determines, based on the indication of the block vector, a reference block in a same picture as the current block for predicting the current block. The decoder applies, based on the indication of the affine transform, the affine transform parameters to the reference block to generate an affine transformation of the reference block. The decoder decodes the current block based on the residual and the affine transformation of the reference block.

Abstract: A decoder may receive, from a bitstream for a block, an indication of a first bit depth, a residual block of samples of the first bit depth, and a prediction parameter. The decoder may receive, from the bitstream for a sequence, an indication of a second bit depth. The decoder may determine a first decoded block of samples of the first bit depth based on the first bit depth, the residual block of samples of the first bit depth, and the prediction parameter. The decoder may determine a second decoded block of samples of the second bit depth based on the first decoded block of samples of the first bit depth.

Abstract: An encoder may generate, for each of a plurality of block vectors, an intra block compensated prediction of a block. The encoder may select, based on the intra block compensated predictions of the block, a block vector from the plurality of block vectors for the block. The encoder may determine affine transform parameters of the intra block compensated prediction for the block vector. The encoder may signal, in a bit stream, both of an indication of an affine transform of the intra block compensated prediction and the affine transform parameters based on a residual determined for the intra block compensated prediction generated for the block vector and a value of the affine transform parameters.

Abstract: Transcoding bitrate prediction techniques can include receiving a first encoded content. A transcoder bitrate can be estimated based on regression over a video quality estimator of the first encoded content and a second encoded content. The estimated transcoder bitrate can be utilized to transcoding the first encoded content into the second encoded.

Abstract: A decoder receives, from a bitstream for a block vector (BV), an indication of a block vector predictor (BVP). The decoder determines a sign of a first component of a block vector difference (BVD) based on a component of the BV and a component of the BVP. The decoder decodes the BV based on the BVP and the BVD. The decoder generates an intra block compensated prediction of a current block (CB) based on the BV. The decoder decodes the CB based on the intra block compensated prediction and a residual of the CB.

Abstract: A decoder may receive, for a block and from a bit stream, an indication of a decoder-side affine transform, a prediction mode, and a residual block. The decoder may generate a compensated prediction of the block. For example, the decoder may generate the compensated prediction of the block based on the residual block and the prediction mode. The decoder may generate, based on the indication and for each of a plurality of affine transform parameters, an affine transformation of the compensated prediction. The decoder may determine an affine transform parameter, from the plurality of affine transform parameters, based on a visual quality of each of the affine transformations of the compensated prediction.

Abstract: An apparatus determines a value of a coordinate of a sample is outside a range of values of the coordinate for samples in an intra block copy (IBC) reference region. The sample is displaced from a current block by an amount indicated by a candidate block vector predictor (BVP). Based on determining the value of the coordinate of the sample is outside the range of value of the coordinate for the samples in the IBC reference region, the apparatus adjusts a component of the candidate BVP to generate an adjusted candidate BVP. The apparatus constructs a list of candidate BVPs comprising the adjusted candidate BVP. The apparatus derives costs for the candidate BVPs in the list. The apparatus reorders the candidate BVPs in the list based on the costs.

Abstract: Scene aware video content encoding techniques can determine if video content is a given content type and is one of one or more given titles that include one or more given scenes. The one or more given scenes of the video content of the given type and given one of the titles can be encoded using corresponding scenes specific encoding parameter values, and the non-given scenes can be encoded using one or more general encoding parameter values. The one or more given titles can be selected based on a rate of streaming of various video content titles of the given type.

Abstract: In some embodiments, a decoder may receive, from a bit stream for a block vector, an indication of a block vector predictor and a block vector difference. A sign of a directional component of the block vector difference may be determined based on: a directional component of the block vector, and a directional component of the block vector predictor. The decoder may decode the block vector based on the block vector predictor and the block vector difference. The decoder may generate an intra block compensated prediction of a block based on the block vector. The decoder may decode the block based on the intra block compensated prediction of the block and a prediction residual of the block.

Abstract: Encoding and/or decoding a block of a video frame may be based on a previously decoded reference block in the same frame or in a different frame. The reference block may be indicated by a block vector (BV). The BV may be encoded as difference between a block vector predictor (BVP) and the BV. The BVP may be adjusted to improve prediction accuracy of the BVP.

Abstract: An apparatus determines a value of a coordinate for a sample is outside a range of values of the coordinate for samples in a reference region. The sample is displaced relative to a current block by an amount indicated by a block vector predictor (BVP). The apparatus adjusts a component, corresponding to a direction of the coordinate, of the BVP to have an adjusted value closer to the range of values of the coordinate for the samples in the reference region based on the determining. The apparatus uses the BVP, with the component adjusted to have the adjusted value, to determine or predict a block vector (BV) for the current block.

Abstract: An apparatus calculates a block vector difference (BVD) between a block vector (BV) and a block vector predictor (BVP). The apparatus determines each of a plurality of BV candidates based on a sum of the BVP and a different one of a plurality of BVD candidates. Each of the plurality of BVD candidates comprises: a first and a second component magnitude of the BVD; and a different combination of signs for the first and second component magnitudes. The apparatus determines validities of the plurality of BV candidates based on values of samples, stored in a reference memory, of reference blocks indicated by the plurality of BV candidates. The apparatus signales, in a bitstream, a sign for at least one of the first and second component magnitudes of the BVD based on the validities of the plurality of BV candidates.

Abstract: Encoding and/or decoding a block of a video frame may be based on a previously decoded reference block in the same frame or in a different frame. The reference block may be indicated by a block vector (BV). The BV may be encoded as difference between a block vector predictor (BVP) and the BV. The BVP may be adjusted to improve prediction accuracy of the BVP.

Abstract: A decoder receives, in a bitstream, an indication of a block vector predictor (BVP) and a first and a second component magnitude of a block vector difference (BVD). The decoder determines each of a plurality of BV candidates based on a sum of the BVP and a different one of a plurality of BVD candidates. Each of the plurality of BVD candidates comprises: the first and second component magnitudes; and a different combination of signs for the first and second component magnitudes. The decoder determines a sign for at least one of the first and second component magnitudes of the BVD based on validities of the plurality of BV candidates.

Abstract: A decoder may generate, for each of a plurality of intra prediction modes determined based on a most probable mode (MPM) list for intra prediction of a block, a prediction of at least one neighboring region of the block. The decoder may determine, based on the predictions of the at least one neighboring region, a first intra prediction mode from the plurality of intra prediction modes. The decoder may decode a second intra prediction mode, that is different from the first intra prediction mode, for the block based on the first intra prediction mode and signaling information in a video bitstream.

Abstract: A decoder may determine reference signals of a chroma block. The decoder may decode a decision rule in a bitstream. The decoder may determine a chroma prediction model among one or more linear models and one or more non-linear models based on the decision rule. The decoder may generate a prediction of the chroma block based on the reference signals of the chroma block and the chroma prediction model. The decoder may determine a reconstruction of the chroma block based on the prediction of the chroma block and a decoded residual of the chroma block.

Abstract: Methods and apparatuses for video transcoding based on spatial or temporal importance include: in response to receiving an encoded video bitstream, decoding a picture from the encoded video bitstream; determining a first level of spatial importance for a first region of a background of the picture based on an image segmentation technique; applying to the first region a first resolution-enhancement technique associated with the first level of spatial importance for increasing resolution of the first region by a scaling factor, wherein the first resolution-enhancement technique is selected from a set of resolution-enhancement techniques having different computational complexity levels; and encoding the first region using a video coding standard.

Abstract: The present disclosure relates to a method and an apparatus for map reduce. In some embodiments, an exemplary processing unit includes: a 2-dimensional (2D) processing element (PE) array comprising a plurality of PEs, each PE comprising a first input and a second input, the first inputs of the PEs in a linear array in a first dimension of the PE array being connected in series and the second inputs of the PEs in a linear array in a second dimension of the PE array being connected in parallel, each PE being configured to perform an operation on data from the first input or second input; and a plurality of reduce tree units, each reduce tree unit being coupled with the PEs in a linear array in the first dimension or the second dimension of the PE array and configured to perform a first reduction operation.