mlsanityData to 7 Oct 2026

PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding

arXiv 2007.10985 ↗First posted 21 Jul 2020cs.CVcited by 502

Not on the map. Why?

Abstract (arXiv)

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has been instrumental to many applications in language and vision. Yet, very little is known about its usefulness in 3D point cloud understanding. We see this as an opportunity considering the effort required for annotating data in 3D. In this work, we aim at facilitating research on 3D representation learning. Different from previous works, we focus on high-level scene understanding tasks. To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes. Our findings are extremely encouraging: using a unified triplet of architecture, source dataset, and contrastive loss for pre-training, we achieve improvement over recent best results in segmentation and detection across 6 different benchmarks for indoor and outdoor, real and synthetic datasets -- demonstrating that the learned representation can generalize across domains. Furthermore, the improvement was similar to supervised pre-training, suggesting that future efforts should favor scaling data collection over more detailed annotation. We hope these findings will encourage more research on unsupervised pretext task design for 3D deep learning.

Key facts. Cited by 502 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 96; 2023: 128; 2024: 97; 2025: 89; 2026: 45.

502 papers.

Sort:

By area:

  1. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  2. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  3. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  4. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  5. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  6. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  7. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  8. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  9. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  10. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  11. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  12. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
38 more
  1. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  2. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 159
  3. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  4. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  5. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  6. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  7. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  8. 2022Vision-Centric BEV Perception: A Surveycited by 126
  9. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  10. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  11. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  12. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  13. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  14. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  15. 20213D AffordanceNet: A Benchmark for Visual Object Affordance Understandingcited by 100
  16. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  17. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  18. 2023CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIPcited by 89
  19. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  20. 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
  21. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  22. 2023CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognitioncited by 77
  23. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  24. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  25. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  26. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  27. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  28. 2023CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Datacited by 69
  29. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  30. 2023Rotation-Invariant Transformer for Point Cloud Matchingcited by 68
  31. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  32. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  33. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  34. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  35. 2021Pri3D: Can 3D Priors Help 2D Representation Learning?cited by 61
  36. 2025Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awarenesscited by 61
  37. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  38. 2021DPFM: Deep Partial Functional Mapscited by 58

50 most cited of 502 All 502 (JSON)