mlsanityData to 7 Oct 2026

Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation

arXiv 2207.07522 ↗First posted 15 Jul 2022cs.CV cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Scene flow estimation, which extracts point-wise motion between scenes, is becoming a crucial task in many computer vision tasks. However, all of the existing estimation methods utilize only the unidirectional features, restricting the accuracy and generality. This paper presents a novel scene flow estimation architecture using bidirectional flow embedding layers. The proposed bidirectional layer learns features along both forward and backward directions, enhancing the estimation performance. In addition, hierarchical feature extraction and warping improve the performance and reduce computational overhead. Experimental results show that the proposed architecture achieved a new state-of-the-art record by outperforming other approaches with large margin in both FlyingThings3D and KITTI benchmarks. Codes are available at https://github.com/cwc1260/BiFlow.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 29 of its 50 references that are in the map. First posted on arXiv 15 Jul 2022.

Builds on

29 of 50 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  8. 2018Deep contextualized word representationscited by 2,285
  9. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  10. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  11. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  12. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
17 more
  1. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  2. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  3. 2019Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationcited by 131
  4. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  5. 2019SelFlow: Self-Supervised Learning of Optical Flowcited by 128
  6. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 121
  7. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 108
  8. 2018Conditional BERT Contextual Augmentationcited by 107
  9. 2017Occlusion Aware Unsupervised Learning of Optical Flowcited by 101
  10. 2020FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimationcited by 71
  11. 2020Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motioncited by 41
  12. 2021HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embeddingcited by 36
  13. 2020Hierarchical Attention Learning of Scene Flow in 3D Point Cloudscited by 35
  14. 2019Simple Applications of BERT for Ad Hoc Document Retrievalcited by 34
  15. 2017MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimationcited by 21
  16. 2020Occlusion Guided Scene Flow Estimation on 3D Point Cloudscited by 17
  17. 2021Residual 3D Scene Flow Learning with Context-Aware Feature Extractioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 12; 2024: 16; 2025: 4; 2026: 4.

38 papers.

Sort:

By area:

  1. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  2. 2024ICP-Flow: LiDAR Scene Flow Estimation with ICPcited by 34
  3. 2024DeFlow: Decoder of Scene Flow Network in Autonomous Drivingcited by 29
  4. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  5. 2023Self-Supervised 3D Scene Flow Estimation Guided by Superpointscited by 24
  6. 2023milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensingcited by 20
  7. 2025Zero-Shot Monocular Scene Flow Estimation in the Wildcited by 20
  8. 2023Re-Evaluating LiDAR Scene Flow for Autonomous Drivingcited by 17
  9. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 17
  10. 2023GMSF: Global Matching Scene Flowcited by 14
  11. 2023Multi-Body Neural Scene Flowcited by 12
  12. 2023DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Modelcited by 11
26 more
  1. 2023Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimationcited by 7
  2. 2024DiffSF: Diffusion Models for Scene Flow Estimationcited by 6
  3. 2024OptFlow: Fast Optimization-based Scene Flow Estimation without Supervisioncited by 5
  4. 2024Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signalscited by 5
  5. 2023EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigiditycited by 4
  6. 2022GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flowcited by 3
  7. 2024Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clusteringcited by 3
  8. 2024NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolationcited by 3
  9. 2025TARS: Traffic-Aware Radar Scene Flow Estimationcited by 3
  10. 2025RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Cloudscited by 3
  11. 2023Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Priorcited by 2
  12. 2024FedRSU: Federated Learning for Scene Flow Estimation on Roadside Unitscited by 2
  13. 2024GERA: Geometric Embedding for Efficient Point Registration Analysiscited by 2
  14. 2025Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Drivingcited by 2
  15. 2023Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Cloudscited by 1
  16. 2023Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistencycited by 1
  17. 2024CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenariocited by 1
  18. 2024RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 1
  19. 2024Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Losscited by 1
  20. 2024STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flowcited by 0
  21. 2024EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Supportcited by 0
  22. 2024SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flowcited by 0
  23. 2024UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registrationcited by 0
  24. 2026PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequencescited by 0
  25. 2026Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimationcited by 0
  26. 2026RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimationcited by 0