3D Spatial Recognition Without Spatially Labeled 3D
Zhongzheng Ren, Ishan Misra, Alexander G. Schwing, Rohit Girdhar
2021Year
19Top-tier citations
Abstract
Figure 1: (Left) Our framework, WyPR, jointly learns semantic segmentation and object detection for point cloud data from only scenelevel class tags. We find that encouraging consistency between the two tasks is key. (Right) Sample segmentation results from ScanNet val set, without seeing any point-level labels during training. Please refer to § 4.4 and Appendix F for more analysis and visualizations.
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.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext ecb01f04-2227-438e-997c-b2473d9342ecCited by top-tier papers19
- HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive RegularizationMengtian Li, Yuan Xie, Yunhang Shen, Bo Ke et al.CVPR 2022 · 92 citations
- An MIL-Derived Transformer for Weakly Supervised Point Cloud SegmentationCheng-Kun Yang, Ji-Jia Wu, Kai-Syun Chen, Yung-Yu Chuang et al.CVPR 2022 · 53 citations
- A Simple Vision Transformer for Weakly Semi-supervised 3D Object DetectionDingyuan Zhang, Dingkang Liang, Zhikang Zou, Jingyu Li et al.ICCV 2023 · 36 citations
- Joint Learning of 2D-3D Weakly Supervised Semantic SegmentationHyeokjun Kweon, Kuk-Jin YoonNeurIPS 2022 · 34 citations
- CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic SegmentationLizhao Liu, Zhuangwei Zhuang, Shangxin Huang, Xunlong Xiao et al.ICCV 2023 · 31 citations
Builds on10
- KPConv: Flexible and Deformable Convolution for Point CloudsHugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui et al.ICCV 2019 · 3,193 citations
- Deep Hough Voting for 3D Object Detection in Point CloudsCharles R. Qi, Or Litany, Kaiming He, Leonidas J. GuibasICCV 2019 · 1,467 citations
- Weakly Supervised Object Detection With Segmentation CollaborationXiaoyan Li, Meina Kan, Shiguang Shan, Xilin ChenICCV 2019 · 105 citations
- Weakly Supervised 3D Object Detection from Point CloudsZengyi Qin, Jinglu Wang, Yan LuACM MM 2020 · 68 citations
- Transferable Semi-Supervised 3D Object Detection From RGB-D DataYew Siang Tang, Gim Hee LeeICCV 2019 · 41 citations
Related papers
- LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point CloudsZihui Zhang, Weisheng Dai, Hongtao Wen, Bo YangCVPR 2025
- Semantic Consistency Networks for 3D Object DetectionWenwen Wei, Ping Wei, Nanning ZhengAAAI 2021 · 10 citations
- Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point CloudsJiacheng Wei, Guosheng Lin, Kim-Hui Yap, Tzu-Yi Hung et al.CVPR 2020
- OneFormer3D: One Transformer for Unified Point Cloud SegmentationMaxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila RukhovichCVPR 2024
- 2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level SupervisionCheng-Kun Yang, Min-Hung Chen, Yung-Yu Chuang, Yen-Yu LinICCV 2023 · 30 citations
