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

• URL: http://arxiv.org/abs/2607.24024v2
• Date: Mon, 03 Aug 2026 05:02:12 GMT
• Title: GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal
• Abstract summary: GeoStereo is a unified stereo geometry estimation framework.<n>It couples a feed-forward stereo matching pipeline with a diffusion-based normal estimation branch.<n>It performs reliably in challenging scenarios, including low-light environments.
• Score: 9.795622920077477
• License: http://creativecommons.org/licenses/by/4.0/
• 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/

Related papers

• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching [4.952844628691303]
  LinStereo is a Position-Aware Linear Attention (PALA) module that replaces local recurrence with global aggregation at linear cost.<n>It achieves state-of-the-art-level accuracy on standard benchmarks and strong cross-domain generalization.<n>It achieves the best overall accuracy with consistent gains 28% lower AbsRel on TartanAir-UW, 26% on SQUID, a real-world underwater dataset.
  arXiv  Detail & Related papers  (2026-06-24T05:58:03Z)
• StereoGeo: an end-to-end stereo camera calibration method [0.4943054375935878]
  StereoGeo is an end-to-end network-based approach for stereo camera calibration.<n>Our method estimates the focal lengths and gravity directions of the left and right cameras.
  arXiv  Detail & Related papers  (2026-06-12T16:44:59Z)
• H-OmniStereo: Zero-Shot Omnidirectional Stereo Matching with Heading-Aligned Normal Priors [39.6437115448559]
  H- OmniStereo is a zero-shot omnidirectional stereo matching framework.<n>We construct high-quality synthetic dataset comprising over 2.8 million top-bottom equirectangular stereo pairs.<n>Our approach achieves higher accuracy than existing methods on out-of-domain datasets.
  arXiv  Detail & Related papers  (2026-05-14T15:30:22Z)
• Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification [52.517763621139956]
  3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis.<n>Standard adaptive density control relies on screen-space positional gradients.<n>We present a structure-aware densification framework for 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-30T15:37:20Z)
• Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception [51.687842983240564]
  Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) remains challenging due to the severe geometric discrepancy between oblique UAV imagery and satellite maps.<n>We propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation.<n>Our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
  arXiv  Detail & Related papers  (2026-04-02T08:08:41Z)
• TopoMaskV3: 3D Mask Head with Dense Offset and Height Predictions for Road Topology Understanding [6.043109546012043]
  TopoMaskV3 is a robust, standalone 3D predictor via two novel dense prediction heads.<n>We are the first to address geographic data leakage in road topology evaluation.<n>TopoMaskV3 achieves state-of-the-art 28.5 OLS on a geographically disjoint benchmark.
  arXiv  Detail & Related papers  (2026-03-02T07:33:46Z)
• Dens3R: A Foundation Model for 3D Geometry Prediction [44.13431776180547]
  Dens3R is a 3D foundation model designed for joint geometric dense prediction.<n>By integrating image-pair matching features with intrinsic invariance modeling, Dens3R accurately regresses multiple geometric quantities.
  arXiv  Detail & Related papers  (2025-07-22T07:22:30Z)
• Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model [70.67610495024459]
  Camera-based setups offer a cost-effective option by using stereo depth estimation to generate dense, high-resolution depth maps.<n>Existing omnidirectional stereo matching approaches achieve only limited depth accuracy across diverse environments.<n>We present DFI-OmniStereo, a novel omnidirectional stereo matching method that leverages a large-scale pre-trained foundation model for relative monocular depth estimation.
  arXiv  Detail & Related papers  (2025-03-30T16:24:22Z)
• FoundationStereo: Zero-Shot Stereo Matching [50.79202911274819]
  FoundationStereo is a foundation model for stereo depth estimation.<n>We first construct a large-scale (1M stereo pairs) synthetic training dataset.<n>We then design a number of network architecture components to enhance scalability.
  arXiv  Detail & Related papers  (2025-01-17T01:01:44Z)
• SR-Stereo & DAPE: Stepwise Regression and Pre-trained Edges for Practical Stereo Matching [2.8908326904081334]
  We propose a novel stepwise regression architecture to overcome domain discrepancies. To enhance the edge awareness of models adapting new domains with sparse ground truth, we propose Domain Adaptation based on Pre-trained Edges (DAPE) The proposed SR-Stereo and DAPE are extensively evaluated on SceneFlow, KITTI, Middbury 2014 and ETH3D.
  arXiv  Detail & Related papers  (2024-06-11T05:25:25Z)
• Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation [53.19926259132379]
  We propose a novel method called SHS-Net for oriented normal estimation of point clouds by learning signed hyper surfaces. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. An attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals.
  arXiv  Detail & Related papers  (2023-05-10T03:40:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.