Image decoding method and apparatus, image coding method and apparatus, device and storage medium

1 . An image decoding method, comprising:

decoding an image bitstream and determining a feature reconstruction value corresponding to a current image feature obtained by decoding, wherein the current image feature is a three-dimensional feature matrix;

obtaining an enhanced feature value by performing feature enhancement on the feature reconstruction value, comprising:

for each matrix element in the current image feature, acquiring a feature standard deviation and a standard deviation representation value corresponding to the matrix element in the current image feature;

determining a feature mask corresponding to the matrix element in the current image feature according to the feature standard deviation the standard deviation representation value and a preset defined threshold; and

obtaining the enhanced feature value by performing feature enhancement on the feature reconstruction value based on the feature mask; and

obtaining a reconstructed image block by performing synthesis transformation on the enhanced feature value.

2 . The image decoding method according to claim 1 , wherein the determining a feature mask corresponding to the matrix element in the current image feature according to the feature standard deviation, the standard deviation representation value and a preset defined threshold comprises:

in a case that the feature standard deviation and the standard deviation representation value corresponding to the matrix element meet a preset enhancement condition, setting the feature mask corresponding to the matrix element as a first-type value; and

in a case that the feature standard deviation and the standard deviation representation value corresponding to the matrix element do not meet the preset enhancement condition, setting the feature mask corresponding to the matrix element as a second-type value.

3 . The image decoding method according to claim 2 , wherein, before the in a case that the feature standard deviation and the standard deviation representation value corresponding to the matrix element meet a preset enhancement condition, setting the feature mask corresponding to the matrix element as a first-type value, the method further comprises:

in a case that the feature standard deviation corresponding to the matrix element is greater than the preset defined threshold and the standard deviation representation value is a first-type representation value, determining that the feature standard deviation and the standard deviation representation value corresponding to the matrix element meet the preset enhancement condition; or,

in a case that the feature standard deviation corresponding to the matrix element is less than the preset defined threshold and the standard deviation representation value is a second-type representation value, determining that the feature standard deviation and the standard deviation representation value corresponding to the matrix element meet the preset enhancement condition.

4 . The image decoding method according to claim 2 , wherein the obtaining the enhanced feature value by performing feature enhancement on the feature reconstruction value based on the feature mask comprises:

taking a matrix element with a corresponding feature mask of a first-type value as a target matrix element; and

obtaining the enhanced feature value by performing enhancement on a feature reconstruction value corresponding to the target matrix element.

5 . The image decoding method according to claim 4 , wherein the obtaining the enhanced feature value by performing enhancement on a feature reconstruction value corresponding to the target matrix element comprises:

acquiring the feature reconstruction value, a residual reconstruction value and a predicted feature value corresponding to the target matrix element;

determining a first enhancement value according to a first scaling factor and the residual reconstruction value, and determining a second enhancement value according to a second scaling factor and the predicted feature value; and

determining the enhanced feature value according to the feature reconstruction value, the first enhancement value and the second enhancement value.

6 . The image decoding method according to claim 5 , wherein, before the determining a first enhancement value according to a first scaling factor and the residual reconstruction value, and determining a second enhancement value according to a second scaling factor and the predicted feature value, the method further comprises:

acquiring a feature channel corresponding to the target matrix element; and

determining the first scaling factor and the second scaling factor according to the feature channel, wherein different feature channels correspond to different first scaling factors and second scaling factors.

7 . The image decoding method according to claim 4 , wherein the obtaining the enhanced feature value by performing enhancement on a feature reconstruction value corresponding to the target matrix element comprises:

acquiring the feature reconstruction value and a predicted feature value corresponding to the target matrix element;

determining a first enhancement value according to a first scaling factor and the feature reconstruction value, and determining a second enhancement value according to a second scaling factor and the predicted feature value; and

determining the enhanced feature value according to the first enhancement value and the second enhancement value.

8 . The image decoding method according to claim 4 , wherein the obtaining the enhanced feature value by performing enhancement on a feature reconstruction value corresponding to the target matrix element comprises:

acquiring the feature reconstruction value and a residual reconstruction value corresponding to the target matrix element;

determining a first enhancement value according to a first scaling factor and the feature reconstruction value, and determining a second enhancement value according to a second scaling factor and the residual reconstruction value; and

determining the enhanced feature value according to the first enhancement value and the second enhancement value.

9 . The image decoding method according to claim 4 , wherein the obtaining the enhanced feature value by performing enhancement on a feature reconstruction value corresponding to the target matrix element comprises:

acquiring the feature reconstruction value and a feature standard deviation corresponding to the target matrix element;

determining a first enhancement value according to a first scaling factor and the feature reconstruction value, and determining a second enhancement value according to a second scaling factor and the feature standard deviation; and

determining the enhanced feature value according to the first enhancement value and the second enhancement value.

10 . The image decoding method according to claim 4 , wherein the feature reconstruction value comprises a luminance reconstruction value and a chrominance reconstruction value, and the enhanced feature value comprises a luminance enhanced feature value and a chrominance enhanced feature value;

wherein the obtaining the enhanced feature value by performing enhancement on a feature reconstruction value corresponding to the target matrix element comprises;

obtaining the chrominance enhanced feature value by performing enhancement on a chrominance reconstruction value corresponding to the target matrix element; and

obtaining the luminance enhanced feature value by performing enhancement on a luminance reconstruction value corresponding to the target matrix element.

11 . The image decoding method according to claim 10 , wherein after obtaining the chrominance enhanced feature value by performing enhancement on a chrominance reconstruction value corresponding to the target matrix element, the method further comprises:

determining a first enhancement value according to the luminance reconstruction value and a first scaling factor; and

performing secondary enhancement on the chrominance enhanced feature value according to the first enhancement value.

12 . The image decoding method according to claim 11 , wherein the determining a first enhancement value according to the luminance reconstruction value and a first scaling factor further comprises:

extracting a component indication parameter from the image bitstream; and

in a case that the component indication parameter is a chrominance enhancement type parameter, determining the first enhancement value according to the luminance reconstruction value and the first scaling factor.

13 . The image decoding method according to claim 5 , wherein the decoding an image bitstream and determining a feature reconstruction value corresponding to a current image feature obtained by decoding comprises:

decoding the image bitstream, and determining a residual reconstruction value corresponding to the current image feature obtained by decoding;

obtaining a predicted feature value by performing prediction according to a feature reconstruction value of a reconstructed feature; and

determining the feature reconstruction value corresponding to the current image feature according to the residual reconstruction value and the predicted feature value.

14 . The image decoding method according to claim 13 , wherein after the decoding the image bitstream, and determining a residual reconstruction value corresponding to the current image feature obtained by decoding, the method further comprises:

obtaining the predicted feature value by performing prediction according to an enhanced feature value of the reconstructed feature; and

determining the feature reconstruction value corresponding to the current image feature according to the residual reconstruction value and the predicted feature value.

15 . The image decoding method according to claim 13 , wherein a feature enhancement mode for an enhanced feature value of the reconstructed feature is same as or different from a feature enhancement mode for an enhanced feature value of the current image feature.

16 . The image decoding method according to claim 15 , wherein whether the feature enhancement mode for the enhanced feature value of the reconstructed feature and the feature enhancement mode for the enhanced feature value of the current image feature are the same or different is determined by a syntax flag, and the syntax flag is read from the image bitstream.

17 . The image decoding method according to claim 13 , wherein the obtaining an enhanced feature value by performing feature enhancement on the feature reconstruction value comprises:

extracting a syntax application range parameter from the image bitstream and obtaining feature position information corresponding to the current image feature;

determining an enhancement syntax parameter according to the feature position information and the syntax application range parameter; and

obtaining the enhanced feature value by performing feature enhancement on the feature reconstruction value according to the enhancement syntax parameter.

18 . A decoding device, wherein the decoding device comprises: a processor, a memory, and a decoding program stored on the memory and executable on the processor, the decoding program, when executed by the processor, cause the processor to:

decode an image bitstream and determine a feature reconstruction value corresponding to a current image feature obtained by decoding, wherein the current image feature is a three-dimensional feature matrix;

obtain an enhanced feature value by performing feature enhancement on the feature reconstruction value comprising:

for each matrix element in the current image feature, acquire a feature standard deviation and a standard deviation representation value corresponding to the matrix element in the current image feature;

determine a feature mask corresponding to the matrix element in the current image feature according to the feature standard deviation, the standard deviation representation value and a preset defined threshold; and

obtain the enhanced feature value by performing feature enhancement on the feature reconstruction value based on the feature mask; and

obtain a reconstructed image block by performing synthesis transformation on the enhanced feature value.

19 . A coding device, wherein the coding device comprises: a processor, a memory, and a decoding program and/or an coding program stored on the memory and executable on the processor, the decoding program, when executed by the processor, implementing the image decoding method according to claim 1 .

20 . A non-transitory computer-readable storage medium, wherein the non-transitory-computer-readable storage medium stores an image decoding program and/or an image coding program, the image decoding program, when executed, implementing the image decoding method according to claim 1 .