Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation

TL;DR

This paper introduces Correlate-and-Excite, a real-time stereo matching network that uses guided channel excitation of cost volume and top-k disparity selection, achieving high accuracy with improved efficiency.

Contribution

The paper proposes a novel Guided Cost volume Excitation (GCE) method and a top-k selection approach, enhancing stereo matching performance while reducing computational complexity.

Findings

Outperforms speed-based algorithms on SceneFlow and KITTI datasets.

Achieves competitive accuracy with state-of-the-art methods.

Demonstrates improved efficiency and effectiveness in real-time stereo matching.

Abstract

Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying cost volume aggregation complements 3D convolutions. However, existing methods with spatially varying operations are complex, cost considerable computation time, and cause memory consumption to increase. In this work, we construct Guided Cost volume Excitation (GCE) and show that simple channel excitation of cost volume guided by image can improve performance considerably. Moreover, we propose a novel method of using top-k selection prior to soft-argmin disparity regression for computing the final disparity estimate. Combining our novel contributions, we present an end-to-end network that we call Correlate-and-Excite (CoEx). Extensive experiments of our model on the SceneFlow, KITTI 2012, and KITTI 2015 datasets demonstrate the effectiveness and efficiency of our model and show that our model outperforms other speed-based algorithms while also being competitive to other state-of-the-art algorithms. Codes will be made available at https://github.com/antabangun/coex.