MS-RAFT-3D: A Multi-Scale Architecture for Recurrent Image-Based Scene Flow
Not on the map. Why?
Abstract (arXiv)
Although multi-scale concepts have recently proven useful for recurrent network architectures in the field of optical flow and stereo, they have not been considered for image-based scene flow so far. Hence, based on a single-scale recurrent scene flow backbone, we develop a multi-scale approach that generalizes successful hierarchical ideas from optical flow to image-based scene flow. By considering suitable concepts for the feature and the context encoder, the overall coarse-to-fine framework and the training loss, we succeed to design a scene flow approach that outperforms the current state of the art on KITTI and Spring by 8.7%(3.89 vs. 4.26) and 65.8% (9.13 vs. 26.71), respectively. Our code is available at https://github.com/cv-stuttgart/MS-RAFT-3D.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 2 Jun 2025.
Builds on
17 of 26 references.
References · 17
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
- 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
- 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
- 2022Unifying Flow, Stereo and Depth Estimationcited by 275
- 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
- 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 172
- 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 166
- 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 122
- 2021CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimationcited by 56
- 2021Learning to Segment Rigid Motions from Two Framescited by 46
5 more
- 2019PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimationcited by 20
- 2023CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoningcited by 15
- 2023Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusioncited by 10
- 2022SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selectioncited by 6
- 2023Attentive Multimodal Fusion for Optical and Scene Flowcited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.