mlsanityData to 7 Oct 2026

Point-SAM: Promptable 3D Segmentation Model for Point Clouds

arXiv 2406.17741 ↗First posted 25 Jun 2024cs.CV cs.AIcited by 49

Not on the map. Why?

Abstract (arXiv)

The development of 2D foundation models for image segmentation has been significantly advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D models remains a challenge due to issues such as non-unified data formats, poor model scalability, and the scarcity of labeled data with diverse masks. To this end, we propose a 3D promptable segmentation model Point-SAM, focusing on point clouds. We employ an efficient transformer-based architecture tailored for point clouds, extending SAM to the 3D domain. We then distill the rich knowledge from 2D SAM for Point-SAM training by introducing a data engine to generate part-level and object-level pseudo-labels at scale from 2D SAM. Our model outperforms state-of-the-art 3D segmentation models on several indoor and outdoor benchmarks and demonstrates a variety of applications, such as interactive 3D annotation and zero-shot 3D instance proposal. Codes and demo can be found at https://github.com/zyc00/Point-SAM.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 25 Jun 2024.

Builds on

37 of 45 references.

References · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023Segment Anythingcited by 8,158
  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. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  9. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  10. 2020Point Transformercited by 1,462
  11. 2021Grounded Language-Image Pre-trainingcited by 1,147
  12. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
25 more
  1. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  2. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  3. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  4. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  5. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  6. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  7. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  8. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  9. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  10. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  11. 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 288
  12. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  13. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  14. 2023Segment Any 3D Gaussianscited by 158
  15. 2023SAM3D: Segment Anything in 3D Scenescited by 155
  16. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  17. 2021BRepNet: A topological message passing system for solid modelscited by 92
  18. 2023Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labelscited by 64
  19. 2024Better Call SAL: Towards Learning to Segment Anything in Lidarcited by 47
  20. 2023SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentationcited by 44
  21. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  22. 2023AGILE3D: Attention Guided Interactive Multi-object 3D Segmentationcited by 33
  23. 2022Interactive Object Segmentation in 3D Point Cloudscited by 23
  24. 2023EasyHeC: Accurate and Automatic Hand-eye Calibration via Differentiable Rendering and Space Explorationcited by 16
  25. 2023Generalizable Visual Reinforcement Learning with Segment Anything Modelcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 22; 2026: 23.

49 papers.

Sort:

By area:

  1. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 91
  2. 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 48
  3. 2025P3-SAM: Native 3D Part Segmentationcited by 39
  4. 2024AffordDP: Generalizable Diffusion Policy with Transferable Affordancecited by 35
  5. 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understandingcited by 24
  6. 2024SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Mannerscited by 18
  7. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  8. 2025PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Datacited by 15
  9. 2024GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentationcited by 11
  10. 2026HY3D-Bench: Generation of 3D Assetscited by 11
  11. 2025GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentationcited by 10
  12. 2026SegviGen: Repurposing 3D Generative Model for Part Segmentationcited by 9
37 more
  1. 2025From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMscited by 7
  2. 2026Feedforward 3D Editing Learns from Semantic-Part Transformationcited by 7
  3. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  4. 2024Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Trackingcited by 3
  5. 2025SAM4D: Segment Anything in Camera and LiDAR Streamscited by 3
  6. 2026Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Surveycited by 3
  7. 20263AM: 3egment Anything with Geometric Consistency in Videoscited by 3
  8. 2025GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contractioncited by 2
  9. 2025Easy3D: A Simple Yet Effective Method for 3D Interactive Segmentationcited by 2
  10. 2025Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processescited by 2
  11. 2026VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Modelcited by 2
  12. 2025IPENS:Interactive Unsupervised Framework for Rapid Plant Phenotyping Extraction via NeRF-SAM2 Fusioncited by 1
  13. 2026SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentationcited by 1
  14. 2026Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphscited by 1
  15. 2026R3D: Revisiting 3D Policy Learningcited by 1
  16. 2026PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understandingcited by 1
  17. 2026Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learningcited by 1
  18. 2026SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentationcited by 1
  19. 2025From Flight to Insight: Semantic 3D Reconstruction for Aerial Inspection via Gaussian Splatting and Language-Guided Segmentationcited by 0
  20. 2025PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clickscited by 0
  21. 2025SNAP: Towards Segmenting Anything in Any Point Cloudcited by 0
  22. 2025Rethinking Intermediate Representation for VLM-based Robot Manipulationcited by 0
  23. 2025ArtiBench and ArtiBrain: Benchmarking Generalizable Vision-Language Articulated Object Manipulationcited by 0
  24. 2025S2AM3D: Scale-controllable Part Segmentation of 3D Point Cloudscited by 0
  25. 2025XDen-1K: A Density Field Dataset of Real-World Objectscited by 0
  26. 2025OpenGround: Planning-based Online Perception for Open-World 3D Visual Groundingcited by 0
  27. 2026Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classificationcited by 0
  28. 2026Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshescited by 0
  29. 2026ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddingscited by 0
  30. 2026SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Cloudscited by 0
  31. 2026NegROI: Click-Centric Uncertainty-Guided Refinement with Scene-Conditioned Negative Prompts for Robust Interactive 3D Segmentationcited by 0
  32. 2026Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decompositioncited by 0
  33. 2026SCULPT: Subtractive Composition for 3D Part Generationcited by 0
  34. 2026Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Modelscited by 0
  35. 2026UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interactioncited by 0
  36. 2026S4VY: Segment Anything in Feed-Forward 4D Visual Geometrycited by 0
  37. 2026Point2Part: Unified 3D Partitioning from Point Promptscited by 0