RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

By Lahav Lipson, Zachary Teed, Jia Deng. International Conference on 3D Vision, 2021

683 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/09c8d8249d9e61dace9bd1e0b3cd8042a7ef365d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Chunhua Shen
3. Luc Van Gool
4. Xiaogang Wang
5. Jitendra Malik
6. Ming-Hsuan Yang
7. Trevor Darrell
8. Alan L. Yuille

In Media Technology

1. Wei Yin
2. Dacheng Tao
3. Chi Zhang
4. Jing Zhang
5. Jianfei Cai
6. Chunhua Shen
7. Fisher Yu
8. Xiaozhi Chen

Citations in the corpus

• Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image (2023, methodology): “We use draft-stereo [14] to achieve pseudo-ground truth.”
• Unifying Flow, Stereo and Depth Estimation (2022, methodology): “We compare our GMStereo model with RAFT-Stereo [26] on the Scene Flow test set in Table 7.”
• Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation (2024, neutral): “Deep iterative refinement for geometry: Iterative refinement enables multi-step coarse-to-fine prediction and benefits a wide range of geometry estimation tasks, such as optical flow estimation [46], [75], [76], depth completion [43], [77], [78], and stereo matching [45], [79], [80].”
• Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation (2022, methodology): “Comparison of predicted disparities of repetitivetexture and non-texture cases in smartphone photos with RAFTStereo [23].”