mlsanityData to 7 Oct 2026

FlowNet3D: Learning Scene Flow in 3D Point Clouds

arXiv 1806.01411 ↗First posted 4 Jun 2018cs.CV cs.LGcited by 241

Not on the map. Why?

Abstract (arXiv)

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few try to estimate scene flow directly from point clouds. In this work, we propose a novel deep neural network named FlowNet3D that learns scene flow from point clouds in an end-to-end fashion. Our network simultaneously learns deep hierarchical features of point clouds and flow embeddings that represent point motions, supported by two newly proposed learning layers for point sets. We evaluate the network on both challenging synthetic data from FlyingThings3D and real Lidar scans from KITTI. Trained on synthetic data only, our network successfully generalizes to real scans, outperforming various baselines and showing competitive results to the prior art. We also demonstrate two applications of our scene flow output (scan registration and motion segmentation) to show its potential wide use cases.

Key facts. Cited by 241 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 44; 2022: 51; 2023: 48; 2024: 49; 2025: 28; 2026: 21.

241 papers.

Sort:

By area:

  1. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  2. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 178
  3. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  4. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  5. 2021Neural Scene Flow Priorcited by 91
  6. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  7. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  8. 2025TAPIP3D: Tracking Any Point in Persistent 3D Geometrycited by 67
  9. 2022MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videoscited by 63
  10. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 62
  11. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  12. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
38 more
  1. 2021CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimationcited by 56
  2. 2021Scalable Scene Flow from Point Clouds in the Real Worldcited by 49
  3. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  4. 2021MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronizationcited by 46
  5. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  6. 2022Unbalanced Optimal Transport, from Theory to Numericscited by 45
  7. 2021Self-Supervised Pillar Motion Learning for Autonomous Drivingcited by 44
  8. 2021Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networkscited by 42
  9. 2022IFOR: Iterative Flow Minimization for Robotic Object Rearrangementcited by 42
  10. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  11. 2021StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimationcited by 40
  12. 2021Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walkcited by 39
  13. 2023Fast Neural Scene Flowcited by 39
  14. 2021Accurate Point Cloud Registration with Robust Optimal Transportcited by 38
  15. 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
  16. 2023Geometric Clifford Algebra Networkscited by 37
  17. 2021HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embeddingcited by 36
  18. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  19. 2022Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutionscited by 35
  20. 2024ICP-Flow: LiDAR Scene Flow Estimation with ICPcited by 34
  21. 2025Any4D: Unified Feed-Forward Metric 4D Reconstructioncited by 32
  22. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  23. 2022What Matters for 3D Scene Flow Networkcited by 31
  24. 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
  25. 2021FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Cloudscited by 30
  26. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  27. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  28. 2022Self-Supervised Scene Flow Estimation with 4-D Automotive Radarcited by 29
  29. 2022Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentationcited by 29
  30. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 29
  31. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  32. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  33. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  34. 2022OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstructioncited by 27
  35. 2021Temporally Consistent Online Depth Estimation in Dynamic Scenescited by 26
  36. 2023RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimationcited by 26
  37. 2021Efficient 3D Deep LiDAR Odometrycited by 25
  38. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25

50 most cited of 241 All 241 (JSON)