Self Texture Transfer Networks for Low Bitrate Image Compression

Shoma Iwai, Tomo Miyazaki, Yoshihiro Sugaya, Shinichiro Omachi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 1901-1905

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Iwai_2021_CVPR, author = {Iwai, Shoma and Miyazaki, Tomo and Sugaya, Yoshihiro and Omachi, Shinichiro}, title = {Self Texture Transfer Networks for Low Bitrate Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {1901-1905} }