mlsanityData to 7 Oct 2026

ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation

arXiv 2108.11771 ↗First posted 26 Aug 2021cs.CV cs.ROcited by 18

Not on the map. Why?

Abstract (arXiv)

Separating 3D point clouds into individual instances is an important task for 3D vision. It is challenging due to the unknown and varying number of instances in a scene. Existing deep learning based works focus on a two-step pipeline: first learn a feature embedding and then cluster the points. Such a two-step pipeline leads to disconnected intermediate objectives. In this paper, we propose an integrated reformulation of 3D instance segmentation as a per-point classification problem. We propose ICM-3D, a single-step method to segment 3D instances via instantiated categorization. The augmented category information is automatically constructed from 3D spatial positions. We conduct extensive experiments to verify the effectiveness of ICM-3D and show that it obtains inspiring performance across multiple frameworks, backbones and benchmarks.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

29 of 35 references.

References · 29

  1. 2017Mask R-CNNcited by 7,259
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  9. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  10. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  11. 2019SOLO: Segmenting Objects by Locationscited by 289
  12. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
17 more
  1. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  2. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  3. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  4. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  5. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 145
  6. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  7. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 122
  8. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  9. 2019SSAP: Single-Shot Instance Segmentation With Affinity Pyramidcited by 85
  10. 2020Unseen Object Instance Segmentation for Robotic Environmentscited by 85
  11. 20193D Instance Segmentation via Multi-Task Metric Learningcited by 79
  12. 2020Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentationcited by 64
  13. 2017Repulsion Loss: Detecting Pedestrians in a Crowdcited by 62
  14. 2019EasyLabel: A Semi-Automatic Pixel-wise Object Annotation Tool for Creating Robotic RGB-D Datasetscited by 58
  15. 2019Point Cloud Instance Segmentation using Probabilistic Embeddingscited by 52
  16. 2021RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networkscited by 15
  17. 2017SceneCut: Joint Geometric and Object Segmentation for Indoor Scenescited by 9

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 10; 2024: 1; 2025: 1.

18 papers.

Sort:

By area:

  1. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  2. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  3. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  4. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  5. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  6. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 71
  7. 2023Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learningcited by 55
  8. 2023Understanding Imbalanced Semantic Segmentation Through Neural Collapsecited by 46
  9. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  10. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  11. 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 29
  12. 2023UniGS: Unified Representation for Image Generation and Segmentationcited by 29
6 more
  1. 2024PartSTAD: 2D-to-3D Part Segmentation Task Adaptationcited by 18
  2. 2023Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fieldscited by 12
  3. 2023A Review of Panoptic Segmentation for Mobile Mapping Point Cloudscited by 8
  4. 2023Rethinking Evaluation Metrics of Open-Vocabulary Segmentaioncited by 7
  5. 2022Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densitiescited by 5
  6. 2025PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clickscited by 0