Learned Image Compression with Soft Bit-Based Rate-Distortion Optimization

David Alexandre, Chih Peng Chang, Wen Hsiao Peng, Hsueh Ming Hang

研究成果: Conference contribution同行評審

摘要

This paper introduces the notion of soft bits to address the rate-distortion optimization for learning-based image compression. Recent methods for such compression train an autoencoder end-to-end with an objective to strike a balance between distortion and rate. They are faced with the zero gradient issue due to quantization and the difficulty of estimating the rate accurately. Inspired by soft quantization, we represent quantization indices of feature maps with differentiable soft bits. This allows us to couple tightly the rate estimation with context-adaptive binary arithmetic coding. It also provides a differentiable distortion objective function. Experimental results show that our approach achieves the state-of-the-art compression performance among the learning-based schemes in terms of MS-SSIM and PSNR.

原文English
主出版物標題2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
發行者IEEE Computer Society
頁面1715-1719
頁數5
ISBN(電子)9781538662496
DOIs
出版狀態Published - 九月 2019
事件26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan
持續時間: 22 九月 201925 九月 2019

出版系列

名字Proceedings - International Conference on Image Processing, ICIP
2019-September
ISSN(列印)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
國家Taiwan
城市Taipei
期間22/09/1925/09/19

指紋 深入研究「Learned Image Compression with Soft Bit-Based Rate-Distortion Optimization」主題。共同形成了獨特的指紋。

引用此