mlsanityData to 14 Oct 2026

Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts

arXiv 2012.09165 ↗First posted 16 Dec 2020cs.CVcited by 210

Not on the map. Why?

Abstract (arXiv)

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be accessed and scanned might be limited; even given sufficient data, acquiring 3D labels (e.g. instance masks) requires intensive human labor. In this paper, we explore data-efficient learning for 3D point cloud. As a first step towards this direction, we propose Contrastive Scene Contexts, a 3D pre-training method that makes use of both point-level correspondences and spatial contexts in a scene. Our method achieves state-of-the-art results on a suite of benchmarks where training data or labels are scarce. Our study reveals that exhaustive labelling of 3D point clouds might be unnecessary; and remarkably, on ScanNet, even using 0.1% of point labels, we still achieve 89% (instance segmentation) and 96% (semantic segmentation) of the baseline performance that uses full annotations.

Key facts. Cited by 210 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 50; 2023: 71; 2024: 37; 2025: 26; 2026: 14.

210 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  2. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 303
  3. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 246
  4. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  5. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 125
  6. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 122
  7. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 118
  8. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 113
  9. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  10. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  11. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 99
  12. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 93
38 more
  1. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  2. 2023CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIPcited by 89
  3. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  4. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 86
  5. 2023Rotation-Invariant Transformer for Point Cloud Matchingcited by 69
  6. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  7. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  8. 2021Pri3D: Can 3D Priors Help 2D Representation Learning?cited by 61
  9. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  10. 2023Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learningcited by 56
  11. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  12. 2021SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representationscited by 55
  13. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
  14. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  15. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 54
  16. 2023PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detectioncited by 53
  17. 2023NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detectioncited by 51
  18. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 50
  19. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  20. 2024Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understandingcited by 49
  21. 2023Understanding Imbalanced Semantic Segmentation Through Neural Collapsecited by 46
  22. 2024Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learningcited by 45
  23. 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representationscited by 45
  24. 2023SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentationcited by 44
  25. 2021Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Modelscited by 41
  26. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  27. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  28. 2023AGILE3D: Attention Guided Interactive Multi-object 3D Segmentationcited by 33
  29. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 33
  30. 2022ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenescited by 32
  31. 2023Top-Down Beats Bottom-Up in 3D Instance Segmentationcited by 31
  32. 2023UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenescited by 31
  33. 2025DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentationcited by 31
  34. 2022Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learningcited by 30
  35. 2024Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloudcited by 30
  36. 2024Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentationcited by 30
  37. 2023Point2Vec for Self-Supervised Representation Learning on Point Cloudscited by 28
  38. 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Modelscited by 27

50 most cited of 210 All 210 (JSON)