ECSIC: Epipolar Cross Attention for Stereo Image Compression

TL;DR

ECSIC introduces a novel stereo image compression method that leverages epipolar cross attention and stereo context modules to efficiently exploit mutual information between stereo pairs, achieving state-of-the-art results.

Contribution

The paper proposes ECSIC, a new learned stereo image compression framework utilizing epipolar cross attention and stereo context modules for improved joint encoding.

Findings

Achieves state-of-the-art compression performance on Cityscapes and InStereo2k datasets.

Demonstrates the effectiveness of epipolar cross attention in stereo image compression.

Provides fast encoding and decoding speeds.

Abstract

In this paper, we present ECSIC, a novel learned method for stereo image compression. Our proposed method compresses the left and right images in a joint manner by exploiting the mutual information between the images of the stereo image pair using a novel stereo cross attention (SCA) module and two stereo context modules. The SCA module performs cross-attention restricted to the corresponding epipolar lines of the two images and processes them in parallel. The stereo context modules improve the entropy estimation of the second encoded image by using the first image as a context. We conduct an extensive ablation study demonstrating the effectiveness of the proposed modules and a comprehensive quantitative and qualitative comparison with existing methods. ECSIC achieves state-of-the-art performance in stereo image compression on the two popular stereo image datasets Cityscapes and InStereo2k while allowing for fast encoding and decoding.