Perceptual Image Compression Using Relativistic Average Least Squares GANs

Zhengxue Cheng, Ting Fu, Jiapeng Hu, Li Guo, Shihao Wang, Xiongxin Zhao, Dajiang Zhou, Yang Song; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 1895-1900

Abstract


In this work, we provide a detailed description on our submitted methods ANTxNN and ANTxNN_SSIM to Workshop and Challenge on Learned Image Compression (CLIC) 2021. We propose to incorporate Relativistic average Least Squares GANs (RaLSGANs) into Rate-Distortion Optimization for end-to-end training, to achieve perceptual image compression. We also compare two types of discriminator networks and visualize their reconstructed images. Experimental results have validated our method optimized by RaLSGANs can achieve higher subjective quality compared to PSNR, MS-SSIM or LPIPS-optimized models.

Related Material


[pdf]
[bibtex]
@InProceedings{Cheng_2021_CVPR, author = {Cheng, Zhengxue and Fu, Ting and Hu, Jiapeng and Guo, Li and Wang, Shihao and Zhao, Xiongxin and Zhou, Dajiang and Song, Yang}, title = {Perceptual Image Compression Using Relativistic Average Least Squares GANs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {1895-1900} }