mlsanityData to 7 Oct 2026

FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation

arXiv 2011.10147 ↗First posted 19 Nov 2020cs.CV cs.LGcited by 71

Not on the map. Why?

Abstract (arXiv)

Estimating the 3D motion of points in a scene, known as scene flow, is a core problem in computer vision. Traditional learning-based methods designed to learn end-to-end 3D flow often suffer from poor generalization. Here we present a recurrent architecture that learns a single step of an unrolled iterative alignment procedure for refining scene flow predictions. Inspired by classical algorithms, we demonstrate iterative convergence toward the solution using strong regularization. The proposed method can handle sizeable temporal deformations and suggests a slimmer architecture than competitive all-to-all correlation approaches. Trained on FlyingThings3D synthetic data only, our network successfully generalizes to real scans, outperforming all existing methods by a large margin on the KITTI self-supervised benchmark.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 12; 2023: 21; 2024: 24; 2025: 5; 2026: 4.

71 papers.

Sort:

By area:

  1. 2021Neural Scene Flow Priorcited by 91
  2. 2021CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimationcited by 56
  3. 2023Fast Neural Scene Flowcited by 39
  4. 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
  5. 2024SeFlow: A Self-Supervised Scene Flow Method in Autonomous Drivingcited by 38
  6. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  7. 2024ICP-Flow: LiDAR Scene Flow Estimation with ICPcited by 34
  8. 2022What Matters for 3D Scene Flow Networkcited by 31
  9. 2022Self-Supervised Scene Flow Estimation with 4-D Automotive Radarcited by 29
  10. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  11. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  12. 2022OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Cloudscited by 24
38 more
  1. 2023Self-Supervised 3D Scene Flow Estimation Guided by Superpointscited by 24
  2. 2021SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimationcited by 23
  3. 2024Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimationcited by 22
  4. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  5. 2024I Can't Believe It's Not Scene Flow!cited by 21
  6. 2023milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensingcited by 20
  7. 2023Re-Evaluating LiDAR Scene Flow for Autonomous Drivingcited by 17
  8. 2021Residual 3D Scene Flow Learning with Context-Aware Feature Extractioncited by 15
  9. 2023GMSF: Global Matching Scene Flowcited by 14
  10. 2023DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Cloudscited by 14
  11. 20243DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labellingcited by 14
  12. 2024Neural Eulerian Scene Flow Fieldscited by 14
  13. 2022RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 13
  14. 2023ZeroFlow: Scalable Scene Flow via Distillationcited by 13
  15. 2023Multi-Body Neural Scene Flowcited by 12
  16. 2021Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Cloudscited by 11
  17. 2023DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Modelcited by 11
  18. 2023Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusioncited by 10
  19. 2023Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Cloudscited by 9
  20. 2022Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functionscited by 7
  21. 2023Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimationcited by 7
  22. 2024DiffSF: Diffusion Models for Scene Flow Estimationcited by 6
  23. 2022RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Cloudscited by 5
  24. 2024OptFlow: Fast Optimization-based Scene Flow Estimation without Supervisioncited by 5
  25. 2024Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signalscited by 5
  26. 2024Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizationscited by 5
  27. 2024FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagationcited by 5
  28. 2022Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labelscited by 3
  29. 2022GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flowcited by 3
  30. 2023ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Cloudscited by 3
  31. 2024Self-Supervised Multi-Frame Neural Scene Flowcited by 3
  32. 2024Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clusteringcited by 3
  33. 2025TARS: Traffic-Aware Radar Scene Flow Estimationcited by 3
  34. 20224DAC: Learning Attribute Compression for Dynamic Point Cloudscited by 2
  35. 2023Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Priorcited by 2
  36. 2024FedRSU: Federated Learning for Scene Flow Estimation on Roadside Unitscited by 2
  37. 2024DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagationcited by 2
  38. 2025EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimationcited by 2

50 most cited of 71 All 71 (JSON)