mlsanityData to 7 Oct 2026

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences

arXiv 1910.09165 ↗First posted 21 Oct 2019cs.CV cs.LG cs.ROcited by 117

Not on the map. Why?

Abstract (arXiv)

Understanding dynamic 3D environment is crucial for robotic agents and many other applications. We propose a novel neural network architecture called MeteorNet for learning representations for dynamic 3D point cloud sequences. Different from previous work that adopts a grid-based representation and applies 3D or 4D convolutions, our network directly processes point clouds. We propose two ways to construct spatiotemporal neighborhoods for each point in the point cloud sequence. Information from these neighborhoods is aggregated to learn features per point. We benchmark our network on a variety of 3D recognition tasks including action recognition, semantic segmentation and scene flow estimation. MeteorNet shows stronger performance than previous grid-based methods while achieving state-of-the-art performance on Synthia. MeteorNet also outperforms previous baseline methods that are able to process at most two consecutive point clouds. To the best of our knowledge, this is the first work on deep learning for dynamic raw point cloud sequences.

Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 25; 2023: 32; 2024: 13; 2025: 12; 2026: 13.

117 papers.

Sort:

By area:

  1. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  2. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  3. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  4. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  5. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  6. 2021Neural Scene Flow Priorcited by 91
  7. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  8. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  9. 2021CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimationcited by 56
  10. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  11. 2021Scalable Scene Flow from Point Clouds in the Real Worldcited by 49
  12. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
38 more
  1. 2021MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronizationcited by 46
  2. 2021StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimationcited by 40
  3. 2023Fast Neural Scene Flowcited by 39
  4. 2023Geometric Clifford Algebra Networkscited by 37
  5. 2021HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embeddingcited by 36
  6. 2022Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutionscited by 35
  7. 2022Point Primitive Transformer for Long-Term 4D Point Cloud Video Understandingcited by 35
  8. 2023Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Cloudscited by 34
  9. 2024ICP-Flow: LiDAR Scene Flow Estimation with ICPcited by 34
  10. 2021Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstructioncited by 31
  11. 2022What Matters for 3D Scene Flow Networkcited by 31
  12. 2021FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Cloudscited by 30
  13. 2022Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learningcited by 30
  14. 2022DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objectscited by 29
  15. 2023RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimationcited by 26
  16. 2021Efficient 3D Deep LiDAR Odometrycited by 25
  17. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25
  18. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited 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. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  22. 2021Spatial-Temporal Transformer for 3D Point Cloud Sequencescited by 22
  23. 2023PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videoscited by 22
  24. 20223D Object Detection with a Self-supervised Lidar Scene Flow Backbonecited by 19
  25. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  26. 2023Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videoscited by 19
  27. 2022Revealing Occlusions with 4D Neural Fieldscited by 17
  28. 2023Re-Evaluating LiDAR Scene Flow for Autonomous Drivingcited by 17
  29. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 17
  30. 2023Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videoscited by 16
  31. 2023DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Cloudscited by 14
  32. 2022RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 13
  33. 2023SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentationcited by 13
  34. 2023Multi-Body Neural Scene Flowcited by 12
  35. 2023X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfercited by 12
  36. 2023PCPNet: An Efficient and Semantic-Enhanced Transformer Network for Point Cloud Predictioncited by 11
  37. 2024VG4D: Vision-Language Model Goes 4D Video Recognitioncited by 11
  38. 2024MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Modelscited by 11

50 most cited of 117 All 117 (JSON)