| Full name | RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching |
| Description | 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. |
| Publication title | RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching |
| Publication authors | Lahav Lipson, Zachary Teed, and Jia Deng |
| Publication venue | 3DV |
| Publication URL | https://arxiv.org/abs/2109.07547 |
| Programming language(s) | Pytthon |
| Hardware | RTX 6000 |
| Source code or download URL | https://github.com/princeton-vl/RAFT-Stereo |
| Submission creation date | 5 Nov, 2020 |
| Last edited | 4 Oct, 2021 |
