mlsanityData to 7 Oct 2026

GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud

arXiv 1812.03320 ↗First posted 8 Dec 2018cs.CVcited by 145

Not on the map. Why?

Abstract (arXiv)

We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, which greatly reducing proposals with low objectness.

Key facts. Cited by 145 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 37; 2023: 34; 2024: 20; 2025: 17; 2026: 9.

145 papers.

Sort:

By area:

  1. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  2. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  3. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  4. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  5. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  6. 2022PLA: Language-Driven Open-Vocabulary 3D Scene Understandingcited by 176
  7. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  8. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  9. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  10. 2023Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidancecited by 123
  11. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  12. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
38 more
  1. 2022Superpoint Transformer for 3D Scene Instance Segmentationcited by 115
  2. 2023OneFormer3D: One Transformer for Unified Point Cloud Segmentationcited by 95
  3. 2023RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understandingcited by 93
  4. 2021EfficientLPS: Efficient LiDAR Panoptic Segmentationcited by 76
  5. 2023LEGO-Net: Learning Regular Rearrangements of Objects in Roomscited by 75
  6. 2023OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learningcited by 75
  7. 2021Panoptic 3D Scene Reconstruction From a Single RGB Imagecited by 70
  8. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  9. 2023Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labelscited by 64
  10. 2021Pri3D: Can 3D Priors Help 2D Representation Learning?cited by 61
  11. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  12. 2022CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Cloudscited by 58
  13. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
  14. 2023ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolutioncited by 52
  15. 2023NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detectioncited by 51
  16. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  17. 2024EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understandingcited by 43
  18. 2023Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understandingcited by 38
  19. 2021RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detectioncited by 37
  20. 2021GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Networkcited by 37
  21. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  22. 20223D Instances as 1D Kernelscited by 36
  23. 2023AGILE3D: Attention Guided Interactive Multi-object 3D Segmentationcited by 33
  24. 20213D Spatial Recognition without Spatially Labeled 3Dcited by 31
  25. 2022Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Cloudscited by 31
  26. 2023Top-Down Beats Bottom-Up in 3D Instance Segmentationcited by 31
  27. 2023UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenescited by 31
  28. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  29. 2024Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentationcited by 30
  30. 2022Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarizationcited by 26
  31. 2022GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimationcited by 24
  32. 2023UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentationcited by 24
  33. 2023Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representationcited by 23
  34. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  35. 2023BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Imagecited by 20
  36. 2024UniDet3D: Multi-dataset Indoor 3D Object Detectioncited by 20
  37. 2021ICM-3D: Instantiated Category Modeling for 3D Instance Segmentationcited by 18
  38. 2023EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervisioncited by 18

50 most cited of 145 All 145 (JSON)