Deep Stereo Image Compression via Bi-Directional Coding
Jianjun Lei, Xiangrui Liu, Bo Peng, Dengchao Jin, Wanqing Li, Jingxiao Gu
Abstract
Existing learning-based stereo compression methods usually adopt a unidirectional approach to encoding one image independently and the other image conditioned upon the first. This paper proposes a novel bi-directional coding-based end-to-end stereo image compression network (BCSIC-Net). BCSIC-Net consists of a novel bi-directional contextual transform module which performs nonlinear transform conditioned upon the inter-view context in a latent space to reduce inter-view redundancy, and a bi-directional conditional entropy model that employs inter-view correspondence as a conditional prior to improve coding efficiency. Experimental results on the InStereo2K and KITTI datasets demonstrate that the proposed BCSIC-Net can effectively reduce the inter-view redundancy and outperforms state-of-the-art methods.
BibTeX
@inproceedings{cvpr2022_deepstereoimagec,
title = {Deep Stereo Image Compression via Bi-Directional Coding},
author = {Jianjun Lei and Xiangrui Liu and Bo Peng and Dengchao Jin and Wanqing Li and Jingxiao Gu},
booktitle = {CVPR 2022},
year = {2022}
}