For decoder side mv derivation and refinement

An apparatus, comprising:

• processing circuitry configured to:
• receive a first motion vector and a second motion vector for a first block in a current picture of a video, the first motion vector being indicative of a first reference block in a first picture, and the second motion vector being indicative of a second reference block in a second picture, the current picture being between the first picture and the second picture in the video;
• generate a bilateral template based on a weighted combination of the first reference block and the second reference block;
• determine, by application of a refinement interpolation filter, a refined first motion vector based on the bilateral template and a first set of reference blocks in the first picture, the refined first motion vector indicating a first refined reference block in the first picture;
• determine a refined second motion vector based on the bilateral template and a second set of reference blocks in the second picture, the refined second motion vector indicating a second refined reference block in the second picture;
• determine an initial motion vector of a second block that is coded after the first block according to at least one of the first motion vector and the second motion vector for the first block;
• and
• reconstruct, by application of a final motion compensation interpolation filter, the first block according to (i) the first refined motion vector that is indicative of the first refined reference block in the first picture, and (ii) the second refined motion vector that is indicative of the second refined reference block in the second picture.

A non-transitory computer-readable medium storing instructions which when executed by a computer for video decoding cause the computer to perform:

• receiving a first motion vector and a second motion vector for a first block in a current picture of a video, the first motion vector being indicative of a first reference block in a first picture, and the second motion vector being indicative of a second reference block in a second picture, the current picture being between the first picture and the second picture in the video;
• generating a bilateral template based on a weighted combination of the first reference block and the second reference block;
• determining, by applying a refinement interpolation filter, a refined first motion vector based on the bilateral template and a first set of reference blocks in the first picture, the refined first motion vector indicating a first refined reference block in the first picture;
• determining a refined second motion vector based on the bilateral template and a second set of reference blocks in the second picture, the refined second motion vector indicating a second refined reference block in the second picture;
• determining an initial motion vector of a second block that is coded after the first block according to at least one of the first motion vector and the second motion vector for the first block;
• and
• reconstructing, by applying a final motion compensation interpolation filter, the first block according to (i) the first refined motion vector that is indicative of the first refined reference block in the first picture, and (ii) the second refined motion vector that is indicative of the second refined reference block in the second picture.