mlsanityData to 14 Oct 2026

3D Spatial Recognition without Spatially Labeled 3D

arXiv 2105.06461 ↗First posted 13 May 2021cs.CV cs.AI cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

We introduce WyPR, a Weakly-supervised framework for Point cloud Recognition, requiring only scene-level class tags as supervision. WyPR jointly addresses three core 3D recognition tasks: point-level semantic segmentation, 3D proposal generation, and 3D object detection, coupling their predictions through self and cross-task consistency losses. We show that in conjunction with standard multiple-instance learning objectives, WyPR can detect and segment objects in point cloud data without access to any spatial labels at training time. We demonstrate its efficacy using the ScanNet and S3DIS datasets, outperforming prior state of the art on weakly-supervised segmentation by more than 6% mIoU. In addition, we set up the first benchmark for weakly-supervised 3D object detection on both datasets, where WyPR outperforms standard approaches and establishes strong baselines for future work.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 49 of its 65 references that are in the map. First posted on arXiv 13 May 2021.

Builds on

49 of 65 references.

References · 49

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
37 more
  1. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  2. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  6. 2016Cross-stitch Networks for Multi-task Learningcited by 467
  7. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  8. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  9. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 326
  10. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 217
  11. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  12. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  13. 2017Multi-task Self-Supervised Visual Learningcited by 200
  14. 2015Weakly Supervised Deep Detection Networkscited by 183
  15. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  16. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 146
  17. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  18. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  19. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  20. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  21. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  22. 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
  23. 2019SESS: Self-Ensembling Semi-Supervised 3D Object Detectioncited by 89
  24. 2020Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detectioncited by 80
  25. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  26. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  27. 2020Weakly Supervised 3D Object Detection from Lidar Point Cloudcited by 67
  28. 2016A Large Dataset of Object Scanscited by 64
  29. 2017Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagerycited by 56
  30. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  31. 2020Weakly Supervised 3D Object Detection from Point Cloudscited by 41
  32. 2020Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenescited by 27
  33. 2019Weakly Supervised Object Detection with Segmentation Collaborationcited by 26
  34. 2019Transferable Semi-supervised 3D Object Detection from RGB-D Datacited by 22
  35. 2016Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detectioncited by 9
  36. 20203D for Free: Crossmodal Transfer Learning using HD Mapscited by 7
  37. 2020Improving Point Cloud Semantic Segmentation by Learning 3D Object Detectioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 11; 2024: 3; 2025: 4; 2026: 2.

31 papers.

Sort:

By area:

  1. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  2. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  3. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  4. 2022VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modelingcited by 21
  5. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  6. 2022Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancementcited by 17
  7. 2022LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentationcited by 16
  8. 20232D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervisioncited by 16
  9. 2023Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrastcited by 14
  10. 2023CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentationcited by 12
  11. 20243D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidancecited by 12
  12. 2022Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervisioncited by 11
19 more
  1. 2021Class-agnostic Reconstruction of Dynamic Objects from Videoscited by 8
  2. 2022Total Variation Optimization Layers for Computer Visioncited by 8
  3. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  4. 2023PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fieldscited by 5
  5. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  6. 2022SL3D: Self-supervised-Self-labeled 3D Recognitioncited by 3
  7. 2026P-SLCR: Unsupervised Point Cloud Semantic Segmentation via Prototypes Structure Learning and Consistent Reasoningcited by 2
  8. 2026PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splattingcited by 2
  9. 2022Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotationscited by 1
  10. 2023Cross-modal and Cross-domain Knowledge Transfer for Label-free 3D Segmentationcited by 1
  11. 2023Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentationcited by 1
  12. 2024Bayesian Self-Training for Semi-Supervised 3D Segmentationcited by 1
  13. 2025High-quality Pseudo-labeling for Point Cloud Segmentation with Scene-level Annotationcited by 1
  14. 20253D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinementcited by 1
  15. 2022Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxescited by 0
  16. 2023You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understandingcited by 0
  17. 2023Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labelscited by 0
  18. 2024Smart Feature is What You Needcited by 0
  19. 2025DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentationcited by 0