arxiv:2109.07547

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

Published on Sep 15, 2021

Authors:

Abstract

RAFT-Stereo is a deep learning architecture for rectified stereo that improves upon RAFT by incorporating multi-level convolutional GRUs for efficient information propagation and achieves state-of-the-art performance on stereo vision benchmarks.

AI-generated summary

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.