TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Stereo Disparity Estimation	Middlebury 2014	RAFT-Stereo	D1 Error (2px)	0.0474	# 1
Stereo Depth Estimation	Spring	RAFT-Stereo	1px total	15.273	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/raft-stereo-multilevel-recurrent-field/stereo-disparity-estimation-on-middlebury)](https://paperswithcode.com/sota/stereo-disparity-estimation-on-middlebury?p=raft-stereo-multilevel-recurrent-field)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/raft-stereo-multilevel-recurrent-field/stereo-depth-estimation-on-spring)](https://paperswithcode.com/sota/stereo-depth-estimation-on-spring?p=raft-stereo-multilevel-recurrent-field)`

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

15 Sep 2021 · Lahav Lipson, Zachary Teed, Jia Deng ·

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.

PDF Abstract