Checkerboard Context Model for Efficient Learned Image Compression

Dailan He, Yaoyan Zheng, Baocheng Sun, Yan Wang, Hongwei Qin

CVPR 2021 pp. 14771-14780

doi:10.1109/CVPR46437.2021.01453 /cvpr/2021/he2021cvpr-checkerboard/

Abstract

For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process must be done in a strict scan order, which breaks the parallelization. We propose a parallelizable checkerboard context model (CCM) to solve the problem. Our two-pass checkerboard context calculation eliminates such limitations on spatial locations by re-organizing the decoding order. Speeding up the decoding process more than 40 times in our experiments, it achieves significantly improved computational efficiency with almost the same rate-distortion performance. To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.

PDF CVPR Semantic Scholar

Cite

Text

He et al. "Checkerboard Context Model for Efficient Learned Image Compression." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01453

Markdown

[He et al. "Checkerboard Context Model for Efficient Learned Image Compression." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/he2021cvpr-checkerboard/) doi:10.1109/CVPR46437.2021.01453

BibTeX

@inproceedings{he2021cvpr-checkerboard,
  title     = {{Checkerboard Context Model for Efficient Learned Image Compression}},
  author    = {He, Dailan and Zheng, Yaoyan and Sun, Baocheng and Wang, Yan and Qin, Hongwei},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {14771-14780},
  doi       = {10.1109/CVPR46437.2021.01453},
  url       = {https://mlanthology.org/cvpr/2021/he2021cvpr-checkerboard/}
}