A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present GeoStereo, a new method that improves 3D vision tasks by combining stereo depth estimation and surface normal prediction. They use a special approach called diffusion priors to help the system better understand shapes, especially in tricky areas like dark or reflective surfaces. GeoStereo mixes a fast stereo matching method with a diffusion-based method for normals, allowing them to help each other and make more accurate predictions. Their tests show it works well on several popular 3D vision benchmarks without needing extra training.
stereo matchingsurface normal estimation3D visiondisparitydiffusion priorszero-shot learningKITTI datasetNYUv2 datasetScanNetiBims-1
Authors
Qizhe Wei, Xianda Guo, Shaocong Xu, Hong Li, Runyi Yang, Hao Zhao
Abstract
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 $\textbf{GeoStereo}$, 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. 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 benchmarks, including KITTI and NYUv2, and delivers the best normal estimation accuracy on many real indoor benchmarks, such as iBims-1 and ScanNet. Project page: https://qz-wei.github.io/GeoStereo.github.io/