Neural network video encoding loop filtering in the transformation domain.

Abstract

A video data encoding method, the method comprises: obtaining input data, wherein the input data includes one or more predicted video data, reconstructed video data, quantization parameter data, limit intensity data, or prediction mode data; converting the input data from an input domain to a transformation domain to generate converted video data; applying a neural network (NN)-based loop filter (ILF) to the converted video data to generate filtered video data; and converting the filtered video data from the transformation domain back to the input domain.