mlsanityData to 7 Oct 2026

HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding

arXiv 2105.07751 ↗First posted 17 May 2021cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Scene flow in 3D point clouds plays an important role in understanding dynamic environments. Although significant advances have been made by deep neural networks, the performance is far from satisfactory as only per-point translational motion is considered, neglecting the constraints of the rigid motion in local regions. To address the issue, we propose to introduce the motion consistency to force the smoothness among neighboring points. In addition, constraints on the rigidity of the local transformation are also added by sharing unique rigid motion parameters for all points within each local region. To this end, a high-order CRFs based relation module (Con-HCRFs) is deployed to explore both point-wise smoothness and region-wise rigidity. To empower the CRFs to have a discriminative unary term, we also introduce a position-aware flow estimation module to be incorporated into the Con-HCRFs. Comprehensive experiments on FlyingThings3D and KITTI show that our proposed framework (HCRF-Flow) achieves state-of-the-art performance and significantly outperforms previous approaches substantially.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 25 of its 51 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

25 of 51 references.

References · 25

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  6. 2018Self-Attention with Relative Position Representationscited by 1,112
  7. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  10. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  11. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  12. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
13 more
  1. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  2. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  3. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  4. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  5. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  6. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  7. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  8. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 108
  9. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  10. 2019Just Go with the Flow: Self-Supervised Scene Flow Estimationcited by 98
  11. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  12. 2017Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimationcited by 70
  13. 2019Deep Rigid Instance Scene Flowcited by 54

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 11; 2023: 10; 2024: 11; 2025: 2.

36 papers.

Sort:

By area:

  1. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  2. 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
  3. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  4. 2022What Matters for 3D Scene Flow Networkcited by 31
  5. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  6. 2022Self-Supervised Scene Flow Estimation with 4-D Automotive Radarcited by 29
  7. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 29
  8. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  9. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  10. 2023Self-Supervised 3D Scene Flow Estimation Guided by Superpointscited by 24
  11. 2024Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimationcited by 22
  12. 2024I Can't Believe It's Not Scene Flow!cited by 21
24 more
  1. 2025Zero-Shot Monocular Scene Flow Estimation in the Wildcited by 20
  2. 2023Re-Evaluating LiDAR Scene Flow for Autonomous Drivingcited by 17
  3. 2021Residual 3D Scene Flow Learning with Context-Aware Feature Extractioncited by 15
  4. 2023GMSF: Global Matching Scene Flowcited by 14
  5. 2023DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Cloudscited by 14
  6. 2024Neural Eulerian Scene Flow Fieldscited by 14
  7. 2022RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 13
  8. 2023ZeroFlow: Scalable Scene Flow via Distillationcited by 13
  9. 2023Multi-Body Neural Scene Flowcited by 12
  10. 2023DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Modelcited by 11
  11. 2024DiffSF: Diffusion Models for Scene Flow Estimationcited by 6
  12. 2024Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signalscited by 5
  13. 2022Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labelscited by 3
  14. 2022GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flowcited by 3
  15. 2023Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Priorcited by 2
  16. 2024FedRSU: Federated Learning for Scene Flow Estimation on Roadside Unitscited by 2
  17. 2025Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Drivingcited by 2
  18. 2022Position Embedding Needs an Independent Layer Normalizationcited by 1
  19. 2023Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Cloudscited by 1
  20. 2024RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 1
  21. 2024Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Losscited by 1
  22. 2024EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Supportcited by 0
  23. 2024Long-Term 3D Point Tracking By Cost Volume Fusioncited by 0
  24. 2024SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flowcited by 0