mlsanityData to 7 Oct 2026

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

arXiv 2407.10084 ↗First posted 14 Jul 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Unsupervised 3D instance segmentation aims to segment objects from a 3D point cloud without any annotations. Existing methods face the challenge of either too loose or too tight clustering, leading to under-segmentation or over-segmentation. To address this issue, we propose Part2Object, hierarchical clustering with object guidance. Part2Object employs multi-layer clustering from points to object parts and objects, allowing objects to manifest at any layer. Additionally, it extracts and utilizes 3D objectness priors from temporally consecutive 2D RGB frames to guide the clustering process. Moreover, we propose Hi-Mask3D to support hierarchical 3D object part and instance segmentation. By training Hi-Mask3D on the objects and object parts extracted from Part2Object, we achieve consistent and superior performance compared to state-of-the-art models in various settings, including unsupervised instance segmentation, data-efficient fine-tuning, and cross-dataset generalization. Code is release at https://github.com/ChengShiest/Part2Object

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 51 of its 66 references that are in the map. First posted on arXiv 14 Jul 2024.

Builds on

51 of 66 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023Segment Anythingcited by 8,158
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  10. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  11. 2022Language-driven Semantic Segmentationcited by 711
  12. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
38 more
  1. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  2. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  3. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  4. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  5. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  6. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  7. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  8. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  9. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
  10. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  11. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  12. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  13. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 165
  14. 2023SAM3D: Segment Anything in 3D Scenescited by 155
  15. 2015End-to-end people detection in crowded scenescited by 140
  16. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  17. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  18. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  19. 2022Superpoint Transformer for 3D Scene Instance Segmentationcited by 115
  20. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  21. 2017Accelerated Hierarchical Density Clusteringcited by 100
  22. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  23. 2023OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentationcited by 82
  24. 2018Learning to predict crisp boundariescited by 81
  25. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  26. 2023Contrastive Grouping with Transformer for Referring Image Segmentationcited by 54
  27. 2019Point Cloud Instance Segmentation using Probabilistic Embeddingscited by 52
  28. 2018Fully-Convolutional Point Networks for Large-Scale Point Cloudscited by 44
  29. 2023EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignmentcited by 44
  30. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  31. 2023Top-Down Beats Bottom-Up in 3D Instance Segmentationcited by 31
  32. 2023UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenescited by 31
  33. 2023LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Modelscited by 29
  34. 2022OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Cloudscited by 24
  35. 2023IKEA-Manual: Seeing Shape Assembly Step by Stepcited by 22
  36. 2020Self-Prediction for Joint Instance and Semantic Segmentation of Point Cloudscited by 12
  37. 2024The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Modelscited by 10
  38. 2023FreePoint: Unsupervised Point Cloud Instance Segmentationcited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 3.

12 papers.

  1. 2025Vision Function Layer in Multimodal LLMscited by 17
  2. 2025Rethinking Query-based Transformer for Continual Image Segmentationcited by 14
  3. 2025Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Contextcited by 9
  4. 2025Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formatscited by 6
  5. 2025Sim-DETR: Unlock DETR for Temporal Sentence Groundingcited by 4
  6. 2025Closed-Loop Transfer for Weakly-supervised Affordance Groundingcited by 4
  7. 2026HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Drivingcited by 4
  8. 2025GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervisioncited by 3
  9. 2025No More Sibling Rivalry: Debiasing Human-Object Interaction Detectioncited by 3
  10. 2025Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learningcited by 1
  11. 2026EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervisioncited by 1
  12. 2026FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentationcited by 0