L3C-Stereo: Lossless compression for stereo images

作     者：Huang, Zihao Sun, Zhe Duan, Feng Cichocki, Andrzej Ruan, Peiying Li, Chao 

作者机构：College of Artificial Intelligence Nankai University Tianjin China Computational Engineering Applications Unit Office for Information Systems and Cybersecurity RIKEN Saitama Japan Skolkovo Institute of Science and Technology Moscow Russia College of Computer Science Hangzhou Dianzi University China Department of Informatics Nicolaus Copernicus University Poland Systems Research Institute of Polish of Academy of Science Warsaw Poland NVIDIA AI Technology Center NVIDIA Corporation Japan Japan  RIKEN Japan 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2021年

核心收录：

主　　题：Stereo image processing 

摘      要：A large number of autonomous driving tasks need high-definition stereo images, which requires a large amount of storage space. Efficiently executing lossless compression has become a practical problem. Commonly, it is hard to make accurate probability estimates for each pixel. To tackle this, we propose L3C-Stereo, a multi-scale lossless compression model consisting of two main modules: the warping module and the probability estimation module. The warping module takes advantage of two view feature maps from the same domain to generate a disparity map, which is used to reconstruct the right view so as to improve the confidence of the probability estimate of the right view. The probability estimation module provides pixelwise logistic mixture distributions for adaptive arithmetic coding. In the experiments, our method outperforms the hand-crafted compression methods and the learning-based method on all three datasets used. Then, we show that a better maximum disparity can lead to a better compression effect. Furthermore, thanks to a compression property of our model, it naturally generates a disparity map of an acceptable quality for the subsequent stereo tasks. © 2021, CC BY.