| CPC H04N 19/82 (2014.11) [H04N 19/86 (2014.11)] | 19 Claims |
|
1. A method, the method comprising:
obtaining an input video frame data associated with an input video frame;
performing a deblocking filtering operation on one or more samples included in the input video frame, thereby generating one or more deblocked samples;
performing a machine-learning (ML)-based filtering operation and/or adaptive loop filtering operation on one or more samples included in the input video frame, thereby generating one or more filtered samples; and
using said one or more deblocked samples and/or said one or more filtered samples, producing encoded or decoded video frame data including an encoded or decoded video frame, wherein producing the encoded or decoded video frame data comprises generating a combined value by adding the value of one of said one or more deblocked samples, pdeblocked, to a weighted difference value, (pML-based filtered−pdeblocked)×w, wherein pML-based filtered is a value of one of said one or more filtered samples and w is a weight value, wherein:
the one of said one or more deblocked samples corresponds to a sample in a first sample block of a reconstructed video frame,
the first sample block is adjacent to a second sample block of the reconstructed video frame,
the weight value is determined based on a distance between the one of said one or more deblocked samples and a boundary between the first sample block and the second sample block,
each of the first sample block and the second sample block is either a transform block or a prediction block, and
a block boundary strength, BS, of the boundary is greater than a threshold value.
|