Distortion-Aware Convolutional Neural Network-Based Interpolation Filter for AVS3
Ying Zhang, Liang Wen, Lizhong Wang, Yinji Piao, Weijing Shi, Kwang Pyo Choi
Abstract
Motion compensation is a key technology in video coding for removing the temporal redundancy between video frames. Considering the incompatibility between traditional interpolation filters and diversified video content, the inter prediction method still has considerable room for improvement. This paper proposed a distortion-aware convolutional neural network-based interpolation filter (DA-NNIF) to further improve the interpolation prediction accuracy of sub-pixels with one model. Distortion parameters are introduced into the proposed network to reflect the quantization noise of reference frames. The experimental result shows that the proposed method achieves on average 1.47 % BD-rate reduction on Y component for ClassB, ClassC and ClassD sequences under the random access configuration of AVS3.
BibTeX
@inproceedings{icassp2023_distortionawarec,
title = {Distortion-Aware Convolutional Neural Network-Based Interpolation Filter for AVS3},
author = {Ying Zhang and Liang Wen and Lizhong Wang and Yinji Piao and Weijing Shi and Kwang Pyo Choi},
booktitle = {ICASSP 2023},
year = {2023}
}