GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal

GeoStereo is a unified stereo geometry estimation framework that leverages powerful diffusion priors to jointly predict disparity and surface normals. It couples a feed-forward stereo matching pipeline with a diffusion-based normal estimation branch, enabling strong geometric interaction between the two tasks for more robust 3D understanding in challenging scenarios.

Stereo matching and surface normal estimation are fundamental tasks in 3D vision. However, existing feed-forward stereo methods still struggle to produce reliable predictions in challenging regions, mainly due to the lack of strong geometric priors. In this paper, we propose GeoStereo, a unified stereo geometry estimation framework that leverages powerful diffusion priors to jointly predict disparity and surface normals. Specifically, GeoStereo couples a feed-forward stereo matching pipeline with a diffusion-based normal estimation branch. To enable effective interaction between the two tasks, we introduce a disparity to normal initialization strategy and construct a warp to left-view condition for the diffusion process. Under a shared feature extractor, this coupled design allows the diffusion branch to provide strong structural priors that enhance disparity estimation in ill-posed regions, while the feed-forward branch offers reliable geometric guidance for accurate normal prediction. Extensive experiments show that GeoStereo performs reliably in challenging scenarios, including low-light environments, highly reflective surfaces, and transparent objects. Under zero-shot settings, it achieves Rank-1 disparity estimation on multiple stereo benchmarks, including KITTI and NYUv2, and delivers the best normal estimation accuracy on several real indoor benchmarks, such as iBims-1 and ScanNet, providing an effective solution for robust 3D geometry understanding.