RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching 论文

详细信息

发表期刊/会议

2021 International Conference on 3D Vision (3DV)

发表日期

2021-12-01

发表年份

2021

摘要

We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical flow network RAFT [35]. 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.