Pith. sign in

REVIEW 4 cited by

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

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 2109.07547 v1 pith:VQTEVOP6 submitted 2021-09-15 cs.CV

Lahav Lipson , Zachary Teed , Jia Deng This is my paper · ORCID
classification cs.CV
keywords raft-stereostereointroduceaccurateacrossarchitectureavailablebenchmark
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical flow network RAFT. We introduce multi-level convolutional GRUs, which more efficiently propagate information across the image. A modified version of RAFT-Stereo can perform accurate real-time inference. RAFT-stereo ranks first on the Middlebury leaderboard, outperforming the next best method on 1px error by 29% and outperforms all published work on the ETH3D two-view stereo benchmark. Code is available at https://github.com/princeton-vl/RAFT-Stereo.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. 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...

  2. NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Injecting frozen monocular depth features into neural structured-light decoding cuts Replica-SL depth RMSE ~35% vs NSL and, with depth-centric GICP+sparse anchors+light BA, yields the most stable real D435 SLAM among ...

  3. Neural Field Representations of Mobile Computational Photography

    cs.CV 2025-08 conditional novelty 4.0 of 10

    Fitting neural fields directly to raw phone bursts reconstructs depth, separates reflections and occluders, and stitches panoramas, outperforming the compared baselines on the thesis's benchmarks.

  4. NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces

    cs.CV 2025-06 conditional novelty 4.0 of 10

    In the NTIRE 2025 challenge, four stereo and four monocular teams improved depth estimates on transparent and mirror surfaces over baseline models, with the best monocular methods exceeding 85% on a strict accuracy metric.

Pith tools