Sub-block based constraint on bi-prediction for out-of-boundary conditions

1. A method of decoding performed in a decoder, the method comprising:

receiving coded information of a plurality of subblocks of a current block in a current picture from a coded video bitstream;

obtaining a syntax element indicating a prediction mode associated with the current block in the current picture from the coded video bitstream, the prediction mode being one of a uni-prediction mode and a bi-prediction mode;

determining that the bi-prediction mode is applied to a first subblock of the plurality of subblocks, wherein the first subblock is predicted based on a first reference subblock in a first reference picture and a second reference subblock in a second reference picture;

responsive to the bi-prediction mode being applied to the first subblock of the plurality of subblocks, determining whether (i) a boundary of the first reference subblock is positioned beyond a boundary of the first reference picture and (ii) a boundary of the second reference subblock is positioned within a boundary of the second reference picture; and

responsive to (i) the boundary of the first reference subblock being positioned beyond the boundary of the first reference picture and (ii) the boundary of the second reference subblock being positioned within the boundary of the second reference picture, reconstructing the first subblock of the current block based on the uni-prediction mode such that the first subblock is reconstructed based on the second reference subblock of the second reference picture.

2. The method of claim 1 , wherein the determining that the bi-prediction mode is applied to the first subblock further comprises:

determining that the bi-prediction mode is applied to the first subblock based on one of (i) signaling information that is included in the coded information, (ii) a non-merge inter prediction mode being applied to the current block, and (iii) a merge mode being applied to the current block.

3. The method of claim 1 , wherein the determining whether (i) the boundary of the first reference subblock is positioned beyond the boundary of the first reference picture and (ii) the boundary of the second reference subblock is positioned within the boundary of the second reference picture comprises:

determining whether the boundary of the first reference subblock is positioned beyond the boundary of the first reference picture by a threshold.

4. The method of claim 1 , wherein a size of the first subblock is one of 4 by 4 luma samples and 8 by 8 luma samples based on an inter prediction mode being applied to the current block.

5. The method of claim 1 , further comprising:

responsive to the boundary of the first reference subblock being beyond the boundary of the first reference picture and the boundary of the second reference subblock being beyond the boundary of the second reference picture, reconstructing the first subblock of the current block based on the first reference subblock in the first reference picture and the second reference subblock in the second reference picture.

6. The method of claim 1 , wherein a size of the first subblock is equal to one of:

an affine subblock size based on an affine inter prediction mode being applied to the current block,

a subblock-based temporal motion vector prediction (SbTMVP) subblock size based on a SbTMVP mode being applied to the current block, and

a geometric partitioning mode (GPM) subblock size based on a GPM mode being applied to the current block.

7. The method of claim 1 , further comprising:

responsive to (i) the first subblock being positioned in a blending area that is centered at a geometric partitioning boundary of the current block and (ii) the boundary of the first reference subblock being beyond the boundary of the first reference picture, reconstructing the first subblock based on the second reference subblock in which the boundary of the second reference subblock is positioned within the boundary of the second reference picture.

8. The method of claim 1 , further comprising:

responsive to the first subblock being predicted by the uni-prediction mode, storing uni-prediction motion information of the uni-prediction mode for the first subblock.

9. The method of claim 1 , further comprising:

responsive to at least one pixel of the first subblock being predicted by the uni-prediction mode, storing uni-prediction motion information of the uni-prediction mode for the first subblock.

10. The method of claim 1 , further comprising:

excluding one of a decoder-side motion vector refinement (DMVR) mode, a bi-directional optical flow (BDOF) mode, and a bi-prediction with coding unit-level weight (BCW) mode for the first subblock of the current block responsive to at least one of the boundary of the first reference subblock being beyond the boundary of the first reference picture or the boundary of the second reference subblock being beyond the boundary of the second reference picture.

11. The method of claim 1 , further comprising:

performing a decoder-side motion vector refinement (DMVR) on the first subblock to determine a first prediction subblock based on the first reference subblock in the first reference picture and a second prediction subblock based on the second reference subblock in the second reference picture; and

storing bi-prediction motion information for the first subblock that indicates the first subblock is predicted based on the first prediction subblock in the first reference picture and the second prediction subblock in the second reference picture.

12. An apparatus, comprising:

processing circuitry configured to:

receive coded information of a plurality of subblocks of a current block in a current picture from a coded video bitstream;

obtain a syntax element indicating a prediction mode associated with the current block in the current picture from the coded video bitstream, the prediction mode being one of a uni-prediction mode and a bi-prediction mode;

determine that the bi-prediction mode is applied to a first subblock of the plurality of subblocks, wherein the first subblock is predicted based on a first reference subblock in a first reference picture and a second reference subblock in a second reference picture;

responsive to the bi-prediction mode being applied to the first subblock of the plurality of subblocks, determine whether (i) a boundary of the first reference subblock is positioned beyond a boundary of the first reference picture and (ii) a boundary of the second reference subblock is positioned within a boundary of the second reference picture; and

responsive to (i) the boundary of the first reference subblock being positioned beyond the boundary of the first reference picture and (ii) the boundary of the second reference subblock being positioned within the boundary of the second reference picture, reconstruct the first subblock of the current block based on the uni-prediction mode such that the first subblock is reconstructed based on the second reference subblock of the second reference picture.

13. The apparatus of claim 12 , wherein the processing circuitry is configured to:

determine that the bi-prediction mode is applied to the first subblock based on one of (i) signaling information that is included in the coded information, (ii) a non-merge inter prediction mode being applied to the current block, and (iii) a merge mode being applied to the current block.

14. The apparatus of claim 12 , wherein the processing circuitry is configured to:

determine whether the boundary of the first reference subblock is positioned beyond the boundary of the first reference picture by a threshold.

15. The apparatus of claim 12 , wherein a size of the first subblock is one of 4 by 4 luma samples and 8 by 8 luma samples based on an inter prediction mode being applied to the current block.

16. The apparatus of claim 12 , wherein the processing circuitry is configured to:

responsive to the boundary of the first reference subblock being beyond the boundary of the first reference picture and the boundary of the second reference subblock being beyond the boundary of the second reference picture, reconstruct the first subblock of the current block based on the first reference subblock in the first reference picture and the second reference subblock in the second reference picture.

17. The apparatus of claim 12 , wherein a size of the first subblock is equal to one of:

an affine subblock size based on an affine inter prediction mode being applied to the current block,

a subblock-based temporal motion vector prediction (SbTMVP) subblock size based on a SbTMVP mode being applied to the current block, and

a geometric partitioning mode (GPM) subblock size based on a GPM mode being applied to the current block.

18. The apparatus of claim 12 wherein the processing circuitry is configured to:

responsive to (i) the first subblock being positioned in a blending area that is centered at a geometric partitioning boundary of the current block and (ii) the boundary of the first reference subblock being beyond the boundary of the first reference picture, reconstruct the first subblock based on the second reference subblock in which the boundary of the second reference subblock is positioned within the boundary of the second reference picture.

19. The apparatus of claim 12 , wherein the processing circuitry is configured to:

responsive to the first subblock being predicted by the uni-prediction mode, store uni-prediction motion information of the uni-prediction mode for the first subblock.

20. The apparatus of claim 12 , wherein the processing circuitry is configured to:

responsive to at least one pixel of the first subblock being predicted by the uni-prediction mode, store uni-prediction motion information of the uni-prediction mode for the first subblock.