User-Guided Variable Rate Learned Image Compression

Rushil Gupta, Suryateja Bv, Nikhil Kapoor, Rajat Jaiswal, Sharmila Nangi, Kuldeep Kulkarni

CVPRW 2022 pp. 1752-1757

doi:10.1109/CVPRW56347.2022.00185 /cvprw/2022/gupta2022cvprw-userguided/

Abstract

We propose a learning-based image compression method that achieves any arbitrary input bitrate via user-guided bit allocation to preferred regions. We verify our hypothesis of incorporating user guidance for bitrate control by experimenting with alternatives that do not have any guidance. We conduct extensive evaluation on CelebA-HQ and CityScapes dataset using standard quantitative metrics and human studies showing that our single model for multiple bitrates achieves similar or better performance as com-pared to previous learned image compression methods that require re-training for each new bitrate.

CVPRW Semantic Scholar

Cite

Text

Gupta et al. "User-Guided Variable Rate Learned Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00185

Markdown

[Gupta et al. "User-Guided Variable Rate Learned Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/gupta2022cvprw-userguided/) doi:10.1109/CVPRW56347.2022.00185

BibTeX

@inproceedings{gupta2022cvprw-userguided,
  title     = {{User-Guided Variable Rate Learned Image Compression}},
  author    = {Gupta, Rushil and Bv, Suryateja and Kapoor, Nikhil and Jaiswal, Rajat and Nangi, Sharmila and Kulkarni, Kuldeep},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {1752-1757},
  doi       = {10.1109/CVPRW56347.2022.00185},
  url       = {https://mlanthology.org/cvprw/2022/gupta2022cvprw-userguided/}
}