Pith. sign in

REVIEW 10 cited by

OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.00343 v8 pith:7MM3HWKM submitted 2023-12-01 cs.CV

Xianda Guo , Chenming Zhang , Juntao Lu , Yiqun Duan , Yiqi Wang , Tian Yang , Zheng Zhu , Long Chen This is my paper
classification cs.CV
keywords matchingstereoopenstereocomprehensiveperformancestereobasestrongavailable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Stereo matching aims to estimate the disparity between matching pixels in a stereo image pair, which is important to robotics, autonomous driving, and other computer vision tasks. Despite the development of numerous impressive methods in recent years, determining the most suitable architecture for practical application remains challenging. Addressing this gap, our paper introduces a comprehensive benchmark focusing on practical applicability rather than solely on individual models for optimized performance. Specifically, we develop a flexible and efficient stereo matching codebase, called OpenStereo. OpenStereo includes training and inference codes of more than 10 network models, making it, to our knowledge, the most complete stereo matching toolbox available. Based on OpenStereo, we conducted experiments and have achieved or surpassed the performance metrics reported in the original paper. Additionally, we conduct an exhaustive analysis and deconstruction of recent developments in stereo matching through comprehensive ablative experiments. These investigations inspired the creation of StereoBase, a strong baseline model. Our StereoBase ranks 1st on SceneFlow, KITTI 2015, 2012 (Reflective) among published methods and achieves the best performance across all metrics. In addition, StereoBase has strong cross-dataset generalization. Code is available at \url{https://github.com/XiandaGuo/OpenStereo}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI

    cs.RO 2026-06 unverdicted novelty 7.0 of 10

    Humanoid-OmniOcc delivers a large-scale panoramic stereo occupancy dataset for humanoid robots via Real2Sim2Real, with a model that outperforms monocular baselines in both unseen sim scenes and real settings.

  2. WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimation

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    WideDepth supplies the first millimeter-accurate indoor fisheye depth benchmark together with a stereo generation pipeline and model adaptation technique.

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

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A unified stereo framework couples feed-forward disparity matching with a diffusion-based normal estimator through disparity-to-normal initialization and warped right-view conditioning, claiming zero-shot SOTA on seve...

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

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A joint stereo–normal framework where a diffusion normal estimator is conditioned on stereo disparity and, through backpropagation, improves zero-shot stereo disparity in ill-posed regions.

  5. AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Depth-conditioned diffusion, geometry self-distillation, and perception frames yield strong zero-shot underwater stereo matching without real underwater labels.

  6. StereoFactory: A Unified Merging Framework for Robust Stereo Matching

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    StereoFactory merges stereo matching foundation models via genetic subset search followed by CMA-ES module routing, reporting lower average errors on four benchmarks than baselines while using 2.7-3.7% of retraining time.

  7. Lite Any Stereo: Efficient Zero-Shot Stereo Matching

    cs.CV 2025-11 unverdicted novelty 6.0 of 10

    Lite Any Stereo delivers top-ranked zero-shot accuracy on four real-world stereo benchmarks using a lightweight backbone, hybrid cost aggregation, and three-stage training on million-scale data, at less than 1% of typ...

  8. Iterative Volume Fusion for Asymmetric Stereo Matching

    cs.CV 2025-08 conditional novelty 6.0 of 10

    IVF-AStereo fuses correlation and concatenation cost volumes in two phases to keep stereo disparity accurate when camera views differ in resolution or color.

  9. Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    LAS2 is a series of efficient stereo matching models that reach state-of-the-art zero-shot performance among fast methods while running 1.8-2.7x faster than prior iterative approaches on H200 and Orin hardware.

  10. ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    ROVR is a new diverse depth dataset for autonomous driving with 200K frames, released pipelines, and ablations showing sparse ground truth supports model training.

Pith tools