Generalized Geometry Encoding Volume for Real-time Stereo Matching

TL;DR

This paper introduces GGEV, a real-time stereo matching network that encodes domain-invariant geometric priors to improve generalization across unseen scenes, achieving state-of-the-art results.

Contribution

The paper proposes a novel GGEV framework with depth-aware features and a dynamic cost aggregation module for enhanced generalization in stereo matching.

Findings

Outperforms existing real-time methods in zero-shot generalization

Achieves state-of-the-art results on KITTI and ETH3D benchmarks

Efficiently encodes geometric priors for robust disparity estimation

Abstract

Real-time stereo matching methods primarily focus on enhancing in-domain performance but often overlook the critical importance of generalization in real-world applications. In contrast, recent stereo foundation models leverage monocular foundation models (MFMs) to improve generalization, but typically suffer from substantial inference latency. To address this trade-off, we propose Generalized Geometry Encoding Volume (GGEV), a novel real-time stereo matching network that achieves strong generalization. We first extract depth-aware features that encode domain-invariant structural priors as guidance for cost aggregation. Subsequently, we introduce a Depth-aware Dynamic Cost Aggregation (DDCA) module that adaptively incorporates these priors into each disparity hypothesis, effectively enhancing fragile matching relationships in unseen scenes. Both steps are lightweight and complementary, leading to the construction of a generalized geometry encoding volume with strong generalization capability. Experimental results demonstrate that our GGEV surpasses all existing real-time methods in zero-shot generalization capability, and achieves state-of-the-art performance on the KITTI 2012, KITTI 2015, and ETH3D benchmarks.