mlsanityData to 14 Oct 2026

RAFT-MSF: Self-Supervised Monocular Scene Flow using Recurrent Optimizer

arXiv 2205.01568 ↗First posted 3 May 2022cs.CV cs.LG cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

Learning scene flow from a monocular camera still remains a challenging task due to its ill-posedness as well as lack of annotated data. Self-supervised methods demonstrate learning scene flow estimation from unlabeled data, yet their accuracy lags behind (semi-)supervised methods. In this paper, we introduce a self-supervised monocular scene flow method that substantially improves the accuracy over the previous approaches. Based on RAFT, a state-of-the-art optical flow model, we design a new decoder to iteratively update 3D motion fields and disparity maps simultaneously. Furthermore, we propose an enhanced upsampling layer and a disparity initialization technique, which overall further improves accuracy up to 7.2%. Our method achieves state-of-the-art accuracy among all self-supervised monocular scene flow methods, improving accuracy by 34.2%. Our fine-tuned model outperforms the best previous semi-supervised method with 228 times faster runtime. Code will be publicly available.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 3 May 2022.

Builds on

24 of 43 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  5. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  6. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  7. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  8. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  9. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  10. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  11. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  12. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
12 more
  1. 2019Self-Supervised Monocular Depth Hintscited by 127
  2. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 122
  3. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 109
  4. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  5. 2020Self-Supervised Monocular Scene Flow Estimationcited by 64
  6. 2019FlowNet3D++: Geometric Losses For Deep Scene Flow Estimationcited by 55
  7. 2021Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimationcited by 48
  8. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  9. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  10. 2019Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenescited by 27
  11. 2018Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understandingcited by 24
  12. 2020MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flowcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 3; 2026: 1.

7 papers.

  1. 2025Zero-Shot Monocular Scene Flow Estimation in the Wildcited by 22
  2. 2023Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusioncited by 10
  3. 2025DELTAv2: Accelerating Dense 3D Trackingcited by 10
  4. 2023EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigiditycited by 4
  5. 2025RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Drivingcited by 2
  6. 2023UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimationcited by 1
  7. 2026RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flowcited by 0