mlsanityData to 14 Oct 2026

OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds

arXiv 2210.04458 ↗First posted 10 Oct 2022cs.CV cs.AI cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike all existing methods which usually require a large amount of human annotations for full supervision, we propose the first unsupervised method, called OGC, to simultaneously identify multiple 3D objects in a single forward pass, without needing any type of human annotations. The key to our approach is to fully leverage the dynamic motion patterns over sequential point clouds as supervision signals to automatically discover rigid objects. Our method consists of three major components, 1) the object segmentation network to directly estimate multi-object masks from a single point cloud frame, 2) the auxiliary self-supervised scene flow estimator, and 3) our core object geometry consistency component. By carefully designing a series of loss functions, we effectively take into account the multi-object rigid consistency and the object shape invariance in both temporal and spatial scales. This allows our method to truly discover the object geometry even in the absence of annotations. We extensively evaluate our method on five datasets, demonstrating the superior performance for object part instance segmentation and general object segmentation in both indoor and the challenging outdoor scenarios.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 63 of its 98 references that are in the map. First posted on arXiv 10 Oct 2022.

Builds on

63 of 98 references.

References · 63

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  10. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  11. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  12. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
38 more
  1. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  2. 2020Object-Centric Learning with Slot Attentioncited by 876
  3. 2018Panoptic Segmentationcited by 802
  4. 2020Convolutional Occupancy Networkscited by 761
  5. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  6. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  7. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  8. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  10. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  11. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  12. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 360
  13. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  14. 2021Conditional Object-Centric Learning from Videocited by 248
  15. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  16. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  17. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  18. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 169
  19. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  20. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  21. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  22. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  23. 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
  24. 2017Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenescited by 122
  25. 2018Learning to Decompose and Disentangle Representations for Video Predictioncited by 121
  26. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  27. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 109
  28. 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108
  29. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 107
  30. 2019Just Go with the Flow: Self-Supervised Scene Flow Estimationcited by 98
  31. 2017SegFlow: Joint Learning for Video Object Segmentation and Optical Flowcited by 92
  32. 2019Unsupervised Learning of Object Structure and Dynamics from Videoscited by 92
  33. 2020Learning multiview 3D point cloud registrationcited by 78
  34. 2020PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Cloudscited by 74
  35. 2019Unsupervised Moving Object Detection via Contextual Information Separationcited by 72
  36. 2020FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimationcited by 71
  37. 2018Deep Part Induction from Articulated Object Pairscited by 66
  38. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 12; 2024: 5; 2025: 5; 2026: 3.

25 papers.

Sort:

By area:

  1. 2023UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenescited by 31
  2. 2023NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videoscited by 28
  3. 2024LISO: Lidar-only Self-Supervised 3D Object Detectioncited by 22
  4. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  5. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  6. 2023EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervisioncited by 18
  7. 2023U3DS3: Unsupervised 3D Semantic Scene Segmentationcited by 16
  8. 2023Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environmentscited by 15
  9. 2025FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocitycited by 13
  10. 2024Part2Object: Hierarchical Unsupervised 3D Instance Segmentationcited by 12
  11. 2025TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videoscited by 11
  12. 2023Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimationcited by 7
13 more
  1. 2023Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Imagescited by 4
  2. 2024Unsupervised semantic segmentation of urban high-density multispectral point cloudscited by 4
  3. 2024Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clusteringcited by 3
  4. 2025SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environmentscited by 3
  5. 2025GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervisioncited by 3
  6. 2024FedRSU: Federated Learning for Scene Flow Estimation on Roadside Unitscited by 2
  7. 2025SSF-PAN: Semantic Scene Flow-Based Perception for Autonomous Navigation in Traffic Scenarioscited by 2
  8. 2023Object Preserving Siamese Network for Single Object Tracking on Point Cloudscited by 1
  9. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  10. 2023Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistencycited by 1
  11. 2026EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervisioncited by 1
  12. 2026CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representationscited by 0
  13. 2026MeshBind: Point-to-Mesh Binding for Non-Rigid Scene Flow Automatic Annotationcited by 0