L3C-Stereo: Lossless Compression for Stereo Images

TL;DR

L3C-Stereo is a novel lossless stereo image compression model that leverages multi-scale features and disparity estimation to outperform existing methods and also provides useful disparity maps for stereo tasks.

Contribution

The paper introduces L3C-Stereo, a new multi-scale lossless compression model that combines warping and probability estimation modules for improved stereo image compression.

Findings

Outperforms existing compression methods on multiple datasets

Better maximum disparity improves compression quality

Generates disparity maps suitable for stereo tasks

Abstract

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 pixel-wise 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.