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

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021)（2021）

引用 4|浏览13

暂无评分

摘要

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.

查看译文

关键词

LPIPS-optimized models,MS-SSIM,PSNR,discriminator networks,ANTxNN_SSIM,CLIC 2021,Challenge on Learned Image Compression 2021,relativistic average least squares GAN,reconstructed images,end-to-end training,Rate-Distortion Optimization,RaLSGAN,perceptual image compression

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要