Perceptual In-Loop Filter for Image and Video Compression

Huairui Wang, Guangjie Ren, Tong Ouyang, Junxi Zhang, Wenwei Han, Zizheng Liu, Zhenzhong Chen

CVPRW 2022 pp. 1769-1772

doi:10.1109/CVPRW56347.2022.00188 /cvprw/2022/wang2022cvprw-perceptual/

Abstract

In this paper, we introduce our hybrid image and video compression scheme enhanced by CNN-optimized in-loop filter. Specifically, a Structure Preserving in-Loop Filter (SPiLF) is incorporated in the hybrid video codec Enhanced Compression Model (ECM), where two branches, i.e., gradient branch and pixel branch, are developed based on the dense residual unit (DRU). To provide pleasant visual quality, the Generative adversarial networks (GAN) loss and LPIPS loss are further considered. Therefore, the proposal is mainly focusing on perceptual-friendly image compression for human vision, whilst video compression could be further investigated. The experiments show that the proposed method achieves advanced visual quality when compared to the traditional methods.

CVPRW Semantic Scholar

Cite

Text

Wang et al. "Perceptual In-Loop Filter for Image and Video Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00188

Markdown

[Wang et al. "Perceptual In-Loop Filter for Image and Video Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/wang2022cvprw-perceptual/) doi:10.1109/CVPRW56347.2022.00188

BibTeX

@inproceedings{wang2022cvprw-perceptual,
  title     = {{Perceptual In-Loop Filter for Image and Video Compression}},
  author    = {Wang, Huairui and Ren, Guangjie and Ouyang, Tong and Zhang, Junxi and Han, Wenwei and Liu, Zizheng and Chen, Zhenzhong},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {1769-1772},
  doi       = {10.1109/CVPRW56347.2022.00188},
  url       = {https://mlanthology.org/cvprw/2022/wang2022cvprw-perceptual/}
}