Ofinno, LLC

Kalyan Goswami

Tae Meon Bae

Esmael Hejazi Dinan

Young-Yoon Lee

Damian Ruiz Coll

In some embodiments, a decoder may receive, from a bit stream, a residual of a block and an indication that the residual was determined based on a refined partition edge. The decoder may determine the refined partition edge based on the indication and reference samples neighboring the block. The decoder may determine based on at least one prediction mode, a prediction for two parts of the block defined by the refined partition edge. The decoder may determine a reconstruction for the block based on the residual and the prediction of the block.

Geometric partitioning refinement

A decoder may generate a reconstruction of a luma block based on a prediction of the luma block and a residual of the luma block. The decoder may generate, at one or more hidden layers, a score distribution. The decoder may generate the score distribution based on the reconstruction of the luma block and one or more coding parameters of the luma block. The decoder may generate, at an output layer and based on the score distribution, a prediction of a chroma block corresponding to the luma block. The decoder may determine a reconstruction of the chroma block based on the prediction of the chroma block and a residual of the chroma block.

Chroma prediction from luma for video coding

A decoder may generate, for each of a plurality of displacement vectors, a prediction of a neighboring region of a block. The decoder may determine, based on the predictions of the neighboring region of the block, a first displacement vector from the plurality of displacement vectors for the neighboring region. The decoder may generate, based on a first predictor candidate list and the first displacement vector, a second predictor candidate list. The decoder may decode a second displacement vector based on: the second predictor candidate list; and signaling information, in a video bitstream, for the block.

Decoder side displacement vector prediction

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.

BVD sign inference in IBC based on BV and BVP components

A decoder may receive, for a block, an indication of decoder-side-prediction and a reconstructed residual block from a bit stream. The decoder may generate, for each respective intra prediction mode of a plurality of intra prediction modes, a reconstructed block based on: a prediction block generated for the respective intra prediction mode; and the reconstructed residual block. The decoder may determine a selected prediction mode, from the plurality of intra prediction modes, for the block based on a visual quality of each of the reconstructed blocks. The decoder may decode the block based on the indication of the decoder-side-prediction and the selected prediction mode.

No reference image quality assessment based decoder side intra prediction

A decoder may receive, in a bit stream for a current block of samples, a first residual block of samples, an indication of a displacement vector, and an indication of a downscaling. The decoder may, based on the indication of the downscaling, upscale the first residual block of samples to a second residual block of samples. The decoder may generate a decoded block of samples based on: the displacement vector; and the second residual block of samples.

Reduced residual inter prediction

A decoder may determine first motion information, from of a plurality of motion information, for a block. The decoder may generate, for each respective motion information of the plurality of motion information, a reconstructed block. The decoder may generate the reconstructed block, for each respective motion information of the plurality of motion information, based on: a prediction block generated for the respective motion information; and a reconstructed residual block based on the first motion information. The decoder may determine second motion information, from the plurality of motion information, for the block based on a visual quality of each of the reconstructed blocks. The decoder may signal, based on the second motion information, the first motion information in a bit stream.

No reference image quality assessment based decoder side inter prediction

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.

Intra prediction

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.

Adaptive block level bit-depth prediction

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.

Growing community of inventors

Reston, VA, United States of America

Kalyan Goswami