mlsanityData to 7 Oct 2026

Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning

arXiv 2006.02598 ↗First posted 4 Jun 2020cs.CV cs.LG eess.IVcited by 68

Not on the map. Why?

Abstract (arXiv)

A major endeavor of computer vision is to represent, understand and extract structure from 3D data. Towards this goal, unsupervised learning is a powerful and necessary tool. Most current unsupervised methods for 3D shape analysis use datasets that are aligned, require objects to be reconstructed and suffer from deteriorated performance on downstream tasks. To solve these issues, we propose to extend the InfoMax and contrastive learning principles on 3D shapes. We show that we can maximize the mutual information between 3D objects and their "chunks" to improve the representations in aligned datasets. Furthermore, we can achieve rotation invariance in SO(3) group by maximizing the mutual information between the 3D objects and their geometric transformed versions. Finally, we conduct several experiments such as clustering, transfer learning, shape retrieval, and achieve state of art results.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 19; 2023: 19; 2024: 13; 2025: 10; 2026: 1.

68 papers.

Sort:

By area:

  1. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  2. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  3. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  4. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  5. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  6. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  7. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  8. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  9. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  10. 2025Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awarenesscited by 61
  11. 2023Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learningcited by 55
  12. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
38 more
  1. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  2. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  3. 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Modelscited by 26
  4. 2024GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understandingcited by 26
  5. 2021Multimodal Semi-Supervised Learning for 3D Objectscited by 24
  6. 2022A Closer Look at Invariances in Self-supervised Pre-training for 3D Visioncited by 24
  7. 2024PCP-MAE: Learning to Predict Centers for Point Masked Autoencoderscited by 23
  8. 20223D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Cloudscited by 18
  9. 2022Rethinking the compositionality of point clouds through regularization in the hyperbolic spacecited by 18
  10. 2023Mutual Information-driven Triple Interaction Network for Efficient Image Dehazingcited by 18
  11. 2023Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph predictioncited by 18
  12. 2024Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learningcited by 16
  13. 2022Masked Surfel Prediction for Self-Supervised Point Cloud Learningcited by 15
  14. 2024RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learningcited by 15
  15. 2023Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understandingcited by 13
  16. 2024What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perceptioncited by 11
  17. 2024HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillationcited by 11
  18. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  19. 2021PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motioncited by 9
  20. 2022Unsupervised Point Cloud Pre-Training via Contrasting and Clusteringcited by 9
  21. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  22. 2024Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detectioncited by 9
  23. 2022PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translationcited by 7
  24. 2025Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Viewscited by 7
  25. 2022Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understandingcited by 6
  26. 2022PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understandingcited by 5
  27. 2022Rethinking Rotation Invariance with Point Cloud Registrationcited by 5
  28. 2024Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classificationcited by 5
  29. 2022COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasetscited by 4
  30. 2023Learning Interpretable Low-dimensional Representation via Physical Symmetrycited by 4
  31. 2023SpeechAct: Towards Generating Whole-body Motion from Speechcited by 4
  32. 2025CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Imagescited by 4
  33. 2024SAM-Guided Masked Token Prediction for 3D Scene Understandingcited by 3
  34. 2021Disentangling Geometric Deformation Spaces in Generative Latent Shape Modelscited by 2
  35. 2022Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Cloudscited by 2
  36. 2023PointSmile: Point Self-supervised Learning via Curriculum Mutual Informationcited by 2
  37. 2023Self-Ordering Point Cloudscited by 2
  38. 2023MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learningcited by 2

50 most cited of 68 All 68 (JSON)