Neural texture transfer assisted video coding with adaptive up-sampling

作者：

Highlights：

• We introduce reference-based SR in down/up-sampling-based video coding method, where target and reference images are not required to be texture-aligned as required in existing methods.

• We proposed an adaptive group of pictures (GOP) method to automatically decide the adaptive sampling scheme.

• The neural texture transfer model for reference-based SR produces realistic up-sampled frame at the decoding end.

摘要

•We introduce reference-based SR in down/up-sampling-based video coding method, where target and reference images are not required to be texture-aligned as required in existing methods.•We proposed an adaptive group of pictures (GOP) method to automatically decide the adaptive sampling scheme.•The neural texture transfer model for reference-based SR produces realistic up-sampled frame at the decoding end.

论文关键词：High-efficiency video coding (HEVC),Reference-based super-resolution,Low bitrate,Video compression,Deep learning,Machine learning

论文评审过程：Received 12 October 2021, Revised 23 May 2022, Accepted 27 May 2022, Available online 3 June 2022, Version of Record 14 June 2022.

论文官网地址：https://doi.org/10.1016/j.image.2022.116754