TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/RAFT-Stereo: Multilevel Recurrent Field Transforms for Ste...

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

Lahav Lipson, Zachary Teed, Jia Deng

2021-09-15Stereo MatchingStereo Depth EstimationOptical Flow EstimationStereo Disparity Estimation
PaperPDFCode(official)

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.

Results

TaskDatasetMetricValueModel
Depth EstimationSpring1px total15.273RAFT-Stereo
3DSpring1px total15.273RAFT-Stereo
Stereo Disparity EstimationMiddlebury 2014D1 Error (2px)4.74RAFT-Stereo
Stereo Depth EstimationSpring1px total15.273RAFT-Stereo

Related Papers

$S^2M^2$: Scalable Stereo Matching Model for Reliable Depth Estimation2025-07-17Channel-wise Motion Features for Efficient Motion Segmentation2025-07-17Cameras as Relative Positional Encoding2025-07-14An Efficient Approach for Muscle Segmentation and 3D Reconstruction Using Keypoint Tracking in MRI Scan2025-07-11Learning to Track Any Points from Human Motion2025-07-08Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts2025-07-07TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation2025-07-07RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather2025-07-02