Depth-aware Volume Attention for Texture-less Stereo Matching

TL;DR

This paper introduces a depth-aware volume attention mechanism to improve stereo matching in texture-less scenarios, achieving state-of-the-art results by emphasizing local structures and hierarchical filtering.

Contribution

It proposes a novel lightweight volume refinement scheme with depth-aware hierarchy and target-aware disparity attention modules for better texture-less stereo matching.

Findings

Achieves state-of-the-art performance on public datasets.

Excels in texture-less and ambiguous regions.

Provides a new depth-wise relative error evaluation metric.

Abstract

Stereo matching plays a crucial role in 3D perception and scenario understanding. Despite the proliferation of promising methods, addressing texture-less and texture-repetitive conditions remains challenging due to the insufficient availability of rich geometric and semantic information. In this paper, we propose a lightweight volume refinement scheme to tackle the texture deterioration in practical outdoor scenarios. Specifically, we introduce a depth volume supervised by the ground-truth depth map, capturing the relative hierarchy of image texture. Subsequently, the disparity discrepancy volume undergoes hierarchical filtering through the incorporation of depth-aware hierarchy attention and target-aware disparity attention modules. Local fine structure and context are emphasized to mitigate ambiguity and redundancy during volume aggregation. Furthermore, we propose a more rigorous evaluation metric that considers depth-wise relative error, providing comprehensive evaluations for universal stereo matching and depth estimation models. We extensively validate the superiority of our proposed methods on public datasets. Results demonstrate that our model achieves state-of-the-art performance, particularly excelling in scenarios with texture-less images. The code is available at https://github.com/ztsrxh/DVANet.