mlsanityData to 7 Oct 2026

Associatively Segmenting Instances and Semantics in Point Clouds

arXiv 1902.09852 ↗First posted 26 Feb 2019cs.CVcited by 86

Not on the map. Why?

Abstract (arXiv)

A 3D point cloud describes the real scene precisely and intuitively.To date how to segment diversified elements in such an informative 3D scene is rarely discussed. In this paper, we first introduce a simple and flexible framework to segment instances and semantics in point clouds simultaneously. Then, we propose two approaches which make the two tasks take advantage of each other, leading to a win-win situation. Specifically, we make instance segmentation benefit from semantic segmentation through learning semantic-aware point-level instance embedding. Meanwhile, semantic features of the points belonging to the same instance are fused together to make more accurate per-point semantic predictions. Our method largely outperforms the state-of-the-art method in 3D instance segmentation along with a significant improvement in 3D semantic segmentation. Code has been made available at: https://github.com/WXinlong/ASIS.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 27; 2023: 19; 2024: 8; 2025: 7; 2026: 4.

86 papers.

Sort:

By area:

  1. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  2. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  3. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  4. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  5. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  6. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  7. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  8. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 98
  9. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  10. 2021HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detectioncited by 47
  11. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  12. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
38 more
  1. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  2. 2023AGILE3D: Attention Guided Interactive Multi-object 3D Segmentationcited by 33
  3. 2023Top-Down Beats Bottom-Up in 3D Instance Segmentationcited by 31
  4. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  5. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 29
  6. 2022Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarizationcited by 26
  7. 2023UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentationcited by 24
  8. 2021Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Cloudscited by 23
  9. 2022Interactive Object Segmentation in 3D Point Cloudscited by 23
  10. 2023Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learningcited by 23
  11. 2021Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoningcited by 22
  12. 2021DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentationcited by 22
  13. 2022Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentationcited by 22
  14. 2021ICM-3D: Instantiated Category Modeling for 3D Instance Segmentationcited by 18
  15. 2024PartSTAD: 2D-to-3D Part Segmentation Task Adaptationcited by 18
  16. 2023Panoptic Vision-Language Feature Fieldscited by 17
  17. 2022PointInst3D: Segmenting 3D Instances by Pointscited by 16
  18. 2021Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Miningcited by 15
  19. 2022Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Datacited by 15
  20. 2022Scalable SoftGroup for 3D Instance Segmentation on Point Cloudscited by 14
  21. 20223D-QueryIS: A Query-based Framework for 3D Instance Segmentationcited by 14
  22. 2023Joint Representation Learning for Text and 3D Point Cloudcited by 14
  23. 2024Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Cloudscited by 14
  24. 2022Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentationcited by 13
  25. 20213D Instance Segmentation of MVS Buildingscited by 12
  26. 2022NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Cloudscited by 12
  27. 2025ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Cloudscited by 12
  28. 2021LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Latticescited by 11
  29. 2022LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Networkcited by 11
  30. 2023Volumetric Semantically Consistent 3D Panoptic Mappingcited by 10
  31. 2021HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensorcited by 9
  32. 2023Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Cloudscited by 9
  33. 2023A Review of Panoptic Segmentation for Mobile Mapping Point Cloudscited by 8
  34. 2023Towards accurate instance segmentation in large-scale LiDAR point cloudscited by 8
  35. 2022PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stagecited by 6
  36. 2023FreePoint: Unsupervised Point Cloud Instance Segmentationcited by 6
  37. 2021Hierarchical Lov'asz Embeddings for Proposal-free Panoptic Segmentationcited by 4
  38. 2022Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitivescited by 4

50 most cited of 86 All 86 (JSON)