Downloads · 30 days
0
RAFT-Stereo
shriarul5273/RAFT-Stereo
RAFT-Stereo is a machine learning model from shriarul5273. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
RAFT-Stereo is a deep learning model for stereo matching introduced in the paper "RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching". It predicts dense disparity maps from rectified left-right ste…
Access
Public
Updated Mar 17, 2026
Repo size
218 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth218 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026
- SHA
- 97526bde
Model card
From the Hugging Face model README
RAFT-Stereo
RAFT-Stereo is a deep learning model for stereo matching introduced in the paper "RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching". It predicts dense disparity maps from rectified left-right stereo image pairs using a recurrent update formulation inspired by RAFT.
Paper: RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching
Venue: 3DV 2021, Best Student Paper Award
Authors: Lahav Lipson, Zachary Teed, Jia Deng
@inproceedings{lipson2021raft,
title={RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching},
author={Lipson, Lahav and Teed, Zachary and Deng, Jia},
booktitle={International Conference on 3D Vision (3DV)},
year={2021}
}
- License
- mit
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026