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}
}