mlsanityData to 7 Oct 2026

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

arXiv 2203.05238 ↗First posted 10 Mar 2022cs.CV cs.AI cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i.e. annotations of object centers). In order to remedy the information loss from box annotations to centers, our method, namely Back to Reality (BR), makes use of synthetic 3D shapes to convert the weak labels into fully-annotated virtual scenes as stronger supervision, and in turn utilizes the perfect virtual labels to complement and refine the real labels. Specifically, we first assemble 3D shapes into physically reasonable virtual scenes according to the coarse scene layout extracted from position-level annotations. Then we go back to reality by applying a virtual-to-real domain adaptation method, which refine the weak labels and additionally supervise the training of detector with the virtual scenes. Furthermore, we propose a more challenging benckmark for indoor 3D object detection with more diversity in object sizes to better show the potential of BR. With less than 5% of the labeling labor, we achieve comparable detection performance with some popular fully-supervised approaches on the widely used ScanNet dataset. Code is available at: https://github.com/wyf-ACCEPT/BackToReality

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

40 of 54 references.

References · 40

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2019Objects as Pointscited by 1,172
  9. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2020Convolutional Occupancy Networkscited by 760
  12. 2017Focal Loss for Dense Object Detectioncited by 749
28 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  2. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  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. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  6. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  7. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  8. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  9. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  10. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  11. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  12. 2021Group-Free 3D Object Detection via Transformerscited by 215
  13. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  14. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  15. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  16. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  17. 2019SESS: Self-Ensembling Semi-Supervised 3D Object Detectioncited by 89
  18. 20203DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detectioncited by 89
  19. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80
  20. 2019Augmentation for small object detectioncited by 73
  21. 2020Weakly Supervised 3D Object Detection from Lidar Point Cloudcited by 67
  22. 2020Weakly Supervised 3D Object Detection from Point Cloudscited by 41
  23. 2019End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scanscited by 40
  24. 2021RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detectioncited by 37
  25. 20213D Spatial Recognition without Spatially Labeled 3Dcited by 31
  26. 2020Deformation-Aware 3D Model Embedding and Retrievalcited by 30
  27. 2019Joint Embedding of 3D Scan and CAD Objectscited by 19
  28. 2015ASIST: Automatic Semantically Invariant Scene Transformationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 4; 2025: 2; 2026: 1.

17 papers.

Sort:

  1. 2023Embodied Task Planning with Large Language Modelscited by 84
  2. 2022Continual Sequence Generation with Adaptive Compositional Modulescited by 31
  3. 2023Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detectioncited by 24
  4. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  5. 2022WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labelscited by 9
  6. 2024Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detectioncited by 6
  7. 2023Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentationcited by 5
  8. 20233D Small Object Detection with Dynamic Spatial Pruningcited by 4
  9. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  10. 2022SL3D: Self-supervised-Self-labeled 3D Recognitioncited by 3
  11. 2024Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detectioncited by 3
  12. 2026Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environmentscited by 2
5 more
  1. 2022Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotationscited by 0
  2. 2023Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labelscited by 0
  3. 2024Smart Feature is What You Needcited by 0
  4. 2024TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detectioncited by 0
  5. 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decodercited by 0