Methods and systems for motion vector calculation and processing

A system, comprising:

• one or more processors and non-transitory memory communicably coupled to a game engine, wherein the memory stores instructions executable by the one or more processors that, when executed, cause the processors to:
• generate a plurality of input image frames;
• calculate one or more internal motion vector (MV) fields between a past frame (PF) and a current frame (CF) of the plurality of input image frames;
• generate a virtual depth for each of the one or more internal MV fields based on a current MV field, a regional foreground MV field, and a regional background MV field of a respective internal MV field;
• generate one or more motion vector with depth (MVD) fields based on the virtual depths of the one or more internal MV fields;
• and
• output the one or more MVD fields for image processing, wherein generating each virtual depth comprises determining a virtual depth for each respective frame based on an initial depth value, a first difference in MVs between the current MV field and the regional foreground MV field and a second difference in MVs between the current MV field and the regional background MV field.

A method, comprising:

• calculating a motion vector (MV) of a first block between a past frame (PF) and a current frame (CF) of an input image, wherein the input image comprises a plurality of pixels partitioned into a plurality of blocks;
• determining potential foreground MVs and potential background MVs for the first block;
• determining reliable foreground MVs and reliable background MVs of the potential foreground and background MVs for a corresponding region, wherein determining the reliable foreground MVs and reliable background MVs of the potential foreground and background MVs is based on previous global foreground MVs, previous global background MVs, previous regional foreground MVs, and previous regional background MVs;
• generating a virtual depth of the first block based at least in part on the reliable foreground and background MVs of the corresponding region, wherein the virtual depth is generated based on a first difference in MVs between a current MV field and the foreground MVs of the corresponding region and a second difference in MVs between the current MV field and the background MVs of the corresponding region;
• decomposing the MV of the first block into a plurality of MVs each of a second, smaller block;
• generating an MV with depth (MVD) for each of the plurality of second, small block MVs based on the virtual depth;
• and
• outputting the MVD for each of the plurality of MVs for image processing.