mlsanityData to 7 Oct 2026

HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds

arXiv 1906.05332 ↗First posted 12 Jun 2019cs.CV cs.LG eess.IVcited by 108

Not on the map. Why?

Abstract (arXiv)

We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds. Inspired by Bilateral Convolutional Layers (BCL), we propose novel DownBCL, UpBCL, and CorrBCL operations that restore structural information from unstructured point clouds, and fuse information from two consecutive point clouds. Operating on discrete and sparse permutohedral lattice points, our architectural design is parsimonious in computational cost. Our model can efficiently process a pair of point cloud frames at once with a maximum of 86K points per frame. Our approach achieves state-of-the-art performance on the FlyingThings3D and KITTI Scene Flow 2015 datasets. Moreover, trained on synthetic data, our approach shows great generalization ability on real-world data and on different point densities without fine-tuning.

Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 22; 2023: 23; 2024: 26; 2025: 10; 2026: 6.

108 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. 2025TAPIP3D: Tracking Any Point in Persistent 3D Geometrycited by 67
  7. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 62
  8. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  9. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
  10. 2021CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimationcited by 56
  11. 2021Scalable Scene Flow from Point Clouds in the Real Worldcited by 49
  12. 2021Self-Supervised Pillar Motion Learning for Autonomous Drivingcited by 44
38 more
  1. 2022IFOR: Iterative Flow Minimization for Robotic Object Rearrangementcited by 42
  2. 2021Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walkcited by 39
  3. 2023Fast Neural Scene Flowcited by 39
  4. 2021Accurate Point Cloud Registration with Robust Optimal Transportcited by 38
  5. 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
  6. 2021HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embeddingcited by 36
  7. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  8. 2024ICP-Flow: LiDAR Scene Flow Estimation with ICPcited by 34
  9. 2022What Matters for 3D Scene Flow Networkcited by 31
  10. 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
  11. 2021FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Cloudscited by 30
  12. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  13. 2022Self-Supervised Scene Flow Estimation with 4-D Automotive Radarcited by 29
  14. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 29
  15. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  16. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  17. 2021Efficient 3D Deep LiDAR Odometrycited by 25
  18. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25
  19. 2022OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Cloudscited by 24
  20. 2023Self-Supervised 3D Scene Flow Estimation Guided by Superpointscited by 24
  21. 2021SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimationcited by 23
  22. 2024I Can't Believe It's Not Scene Flow!cited by 21
  23. 2025Zero-Shot Monocular Scene Flow Estimation in the Wildcited by 20
  24. 20223D Object Detection with a Self-supervised Lidar Scene Flow Backbonecited by 19
  25. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  26. 2023Re-Evaluating LiDAR Scene Flow for Autonomous Drivingcited by 17
  27. 2021Residual 3D Scene Flow Learning with Context-Aware Feature Extractioncited by 15
  28. 2023GMSF: Global Matching Scene Flowcited by 14
  29. 2023DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Cloudscited by 14
  30. 20243DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labellingcited by 14
  31. 2024Neural Eulerian Scene Flow Fieldscited by 14
  32. 2025DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videoscited by 14
  33. 2022RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 13
  34. 2023ZeroFlow: Scalable Scene Flow via Distillationcited by 13
  35. 2023Multi-Body Neural Scene Flowcited by 12
  36. 2025SSF: Sparse Long-Range Scene Flow for Autonomous Drivingcited by 12
  37. 2021Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Cloudscited by 11
  38. 2021LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Latticescited by 11

50 most cited of 108 All 108 (JSON)