ML Anthology

Self Texture Transfer Networks for Low Bitrate Image Compression

Shoma Iwai, Tomo Miyazaki, Yoshihiro Sugaya, Shinichiro Omachi
CVPRW 2021 pp. 1901-1905
doi:10.1109/CVPRW53098.2021.00214 /cvprw/2021/iwai2021cvprw-self/

Abstract

Lossy image compression causes a loss of texture, especially at low bitrate. To mitigate this problem, we propose a novel image compression method that utilizes a reference-based image super-resolution model. We use two image compression models and a self texture transfer model. The image compression models encode and decode a whole input image and selected reference patches. The reference patches are small but compressed with high quality. The self texture transfer model transfers the texture of reference patches into similar regions in the compressed image. The experimental results show that our method can reconstruct accurate texture by transferring the texture of reference patches.

PDF CVPRW Semantic Scholar

Cite

Text

Iwai et al. "Self Texture Transfer Networks for Low Bitrate Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00214

Markdown

[Iwai et al. "Self Texture Transfer Networks for Low Bitrate Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/iwai2021cvprw-self/) doi:10.1109/CVPRW53098.2021.00214

BibTeX

@inproceedings{iwai2021cvprw-self,
  title     = {{Self Texture Transfer Networks for Low Bitrate Image Compression}},
  author    = {Iwai, Shoma and Miyazaki, Tomo and Sugaya, Yoshihiro and Omachi, Shinichiro},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {1901-1905},
  doi       = {10.1109/CVPRW53098.2021.00214},
  url       = {https://mlanthology.org/cvprw/2021/iwai2021cvprw-self/}
}