Stereo Image Coding for Machines with Joint Visual Feature Compression

TL;DR

This paper introduces a novel stereo feature compression network designed for machine vision, significantly improving stereo image compression efficiency and 3D task performance by removing redundancies in stereo visual features.

Contribution

The paper proposes MVSFC-Net, a new neural network architecture for efficient stereo visual feature compression tailored for 3D visual tasks, advancing stereo image coding for machines.

Findings

MVSFC-Net outperforms existing ICM and SIC methods in compression efficiency.

The proposed method enhances 3D visual task performance.

Experimental results demonstrate superior performance over state-of-the-art approaches.

Abstract

2D image coding for machines (ICM) has achieved great success in coding efficiency, while less effort has been devoted to stereo image fields. To promote the efficiency of stereo image compression (SIC) and intelligent analysis, the stereo image coding for machines (SICM) is formulated and explored in this paper. More specifically, a machine vision-oriented stereo feature compression network (MVSFC-Net) is proposed for SICM, where the stereo visual features are effectively extracted, compressed, and transmitted for 3D visual task. To efficiently compress stereo visual features in MVSFC-Net, a stereo multi-scale feature compression (SMFC) module is designed to gradually transform sparse stereo multi-scale features into compact joint visual representations by removing spatial, inter-view, and cross-scale redundancies simultaneously. Experimental results show that the proposed MVSFC-Net obtains superior compression efficiency as well as 3D visual task performance, when compared with the existing ICM anchors recommended by MPEG and the state-of-the-art SIC method.