No reference image quality assessment based decoder side intra prediction
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.
1. A method comprising:
receiving, by a decoder, from a bitstream for a block:
an indication of decoder-side-prediction of an intra prediction mode, wherein a first value of the indication indicates that the intra prediction mode is to be determined by the decoder and a second value of the indication indicates that the intra prediction mode is to be determined from the bitstream; and
a reconstructed residual block;
based on the indication having the first value,
generating, by the decoder, a plurality of reconstructed blocks for a plurality of intra prediction modes, wherein each reconstructed block of the plurality of reconstructed blocks is generated based on:
a prediction block generated for a respective intra prediction mode of the plurality of intra prediction modes; and
the reconstructed residual block;
selecting, by the decoder, a prediction mode, from the plurality of intra prediction modes, as the intra prediction mode of the block based on
a visual quality of each of the plurality of reconstructed blocks; and
decoding, by the decoder, the block based on the intra prediction mode.
2. The method of claim 1 , wherein the receiving comprises:
receiving transform coefficients from the bitstream; and
decoding the transform coefficients to generate the reconstructed residual block.
3. The method of claim 2 , wherein the decoding the transform coefficients to generate the reconstructed residual block comprises:
de-quantizing the transform coefficients; and
inverse transforming the de-quantized transform coefficients.
4. The method of claim 1 , wherein the prediction mode for the block is selected further based on the visual quality, among the visual qualities of the reconstructed blocks, with a highest visual quality.
5. The method of claim 1 , wherein the visual quality of each of the reconstructed blocks is determined without using the block as a reference.
6. The method of claim 1 , wherein the reconstructed block, generated for each respective intra prediction mode of the plurality of intra prediction modes, is generated by summing the prediction block generated for the respective intra prediction mode and the reconstructed residual block.
7. The method of claim 1 , wherein the visual quality of each of the reconstructed blocks is determined based on a visual parameter measurement index.
8. The method of claim 1 , wherein the visual quality of each of the reconstructed blocks is determined based on a deep Learning for Blind Image Quality Assessment.
9. A decoder comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the decoder to:
receive, from a bitstream for a block:
an indication of decoder-side-prediction of an intra prediction mode, wherein a first value of the indication indicates that the intra prediction mode is to be determined by the decoder and a second value of the indication indicates that the intra prediction mode is to be determined from the bitstream; and
a reconstructed residual block;
based on the indication having the first value,
generate a plurality of reconstructed blocks for a plurality of intra prediction modes, wherein each reconstructed block of the plurality of reconstructed blocks is generated based on:
a prediction block generated for a respective intra prediction mode of the plurality of intra prediction modes; and
the reconstructed residual block;
select, by the decoder, a prediction mode, from the plurality of intra prediction modes, as the intra prediction mode of the block based on
a visual quality of each of the plurality of reconstructed blocks; and
decode the block based on the intra prediction mode.
10. The decoder of claim 9 , wherein to receive the reconstructed residual block, the decoder is further caused to:
receive transform coefficients from the bitstream; and
decode the transform coefficients to generate the reconstructed residual block.
11. The decoder of claim 10 , wherein to decode the transform coefficients, the decoder is further caused to:
de-quantize the transform coefficients; and
inverse transform the de-quantized transform coefficients.
12. The decoder of claim 9 , wherein the prediction mode for the block is selected further based on the visual quality, among the visual qualities of the reconstructed blocks, with a highest visual quality.
13. The decoder of claim 9 , wherein the visual quality of each of the reconstructed blocks is determined without using the block as a reference.
14. The decoder of claim 9 , wherein the reconstructed block, generated for each respective intra prediction mode of the plurality of intra prediction modes, is generated by summing the prediction block generated for the respective intra prediction mode and the reconstructed residual block.
15. The decoder of claim 9 , wherein the visual quality of each of the reconstructed blocks is determined based on a visual parameter measurement index.
16. The decoder of claim 9 , wherein the visual quality of each of the reconstructed blocks is determined based on a deep Learning for Blind Image Quality Assessment.
17. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a decoder, cause the decoder to:
receive, from a bitstream for a block:
an indication of decoder-side-prediction of an intra prediction mode, wherein a first value of the indication indicates that the intra prediction mode is to be determined by the decoder and a second value of the indication indicates that the intra prediction mode is to be determined from the bitstream; and
a reconstructed residual block;
based on the indication having the first value,
generate a plurality of reconstructed blocks for a plurality of intra prediction modes, wherein each reconstructed block of the plurality of reconstructed blocks is generated based on:
a prediction block generated for a respective intra prediction mode of the plurality of intra prediction modes; and
the reconstructed residual block;
select a prediction mode, from the plurality of intra prediction modes, as the intra prediction mode of the block based on
a visual quality of each of the plurality of reconstructed blocks; and
decode the block based on the intra prediction mode.
18. The non-transitory computer-readable medium of claim 17 , wherein the prediction mode for the block is selected further based on the visual quality, among the visual qualities of the reconstructed blocks, with a highest visual quality.
19. The non-transitory computer-readable medium of claim 17 , wherein the visual quality of each of the reconstructed blocks is determined without using the block as a reference.
20. The non-transitory computer-readable medium of claim 17 , wherein the reconstructed block, generated for each respective intra prediction mode of the plurality of intra prediction modes, is generated by summing the prediction block generated for the respective intra prediction mode and the reconstructed residual block.