LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds
Zihui Zhang, Weisheng Dai, Hongtao Wen, Bo Yang
2025Year
6Top-tier citations
Abstract
Input Point Cloud GrowSP PointDC PointDC-DINOv2 LogoSP (Ours) Ground Truth Figure 1. Given an input point cloud with complex structures from ScanNet dataset, our LogoSP automatically discovers accurate semantic classes such as sofa and table without needing human labels in training, clearly outperforming all existing baselines.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers6
- UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task AdaptationJiyu Guo, Shuo Yang, Yiming Huang, Yancheng Long et al.NeurIPS 2025 · 4 citations
- PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian SplattingYixiao Song, Qingyong Li, Wen Wang, Zhicheng YanCVPR 2026 · 4 citations
- EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene SupervisionJiahao Chen, Zihui Zhang, Yafei Yang, Jinxi Li et al.CVPR 2026 · 1 citation
- FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object SegmentationZihui Zhang, Zhixuan Sun, Yafei YANG, Jinxi Li et al.ICML 2026
- GeoFree-CoSeg: Unsupervised Point Cloud-Image Cross-Modal Co-Segmentation Without Geometric AlignmentXin Duan, Xiabi Liu, Liyuan PanCVPR 2026
Builds on35
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou et al.ICCV 2021 · 8,921 citations
- KPConv: Flexible and Deformable Convolution for Point CloudsHugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui et al.ICCV 2019 · 3,193 citations
- Invariant Information Clustering for Unsupervised Image Classification and SegmentationXu Ji, Andrea Vedaldi, João F. HenriquesICCV 2019 · 956 citations
- Self-Supervised Pretraining of 3D Features on any Point-CloudZaiwei Zhang, Rohit Girdhar, Armand Joulin, Ishan MisraICCV 2021 · 333 citations
- Unsupervised Point Cloud Pre-training via Occlusion CompletionHanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby et al.ICCV 2021 · 323 citations
Related papers
- GrowSP: Unsupervised Semantic Segmentation of 3D Point CloudsZihui Zhang, Bo Yang, Bing Wang, Bo LiCVPR 2023
- 3D Spatial Recognition Without Spatially Labeled 3DZhongzheng Ren, Ishan Misra, Alexander G. Schwing, Rohit GirdharCVPR 2021
- Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud SegmentationZihao Zhang, Aming Wu, Li Yang, Yahong Han et al.CVPR 2026
- PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel ClusteringZisheng Chen, Hongbin Xu, Weitao Chen, Zhipeng Zhou et al.ICCV 2023 · 21 citations
- 3D-AVS: LiDAR-based 3D Auto-Vocabulary SegmentationWeijie Wei, Osman Ülger, Fatemeh Karimi Nejadasl, Theo Gevers et al.CVPR 2025
