mlsanityData to 7 Oct 2026

PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding

arXiv 2211.12032 ↗First posted 22 Nov 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Some self-supervised cross-modal learning approaches have recently demonstrated the potential of image signals for enhancing point cloud representation. However, it remains a question on how to directly model cross-modal local and global correspondences in a self-supervised fashion. To solve it, we proposed PointCMC, a novel cross-modal method to model multi-scale correspondences across modalities for self-supervised point cloud representation learning. In particular, PointCMC is composed of: (1) a local-to-local (L2L) module that learns local correspondences through optimized cross-modal local geometric features, (2) a local-to-global (L2G) module that aims to learn the correspondences between local and global features across modalities via local-global discrimination, and (3) a global-to-global (G2G) module, which leverages auxiliary global contrastive loss between the point cloud and image to learn high-level semantic correspondences. Extensive experiment results show that our approach outperforms existing state-of-the-art methods in various downstream tasks such as 3D object classification and segmentation. Code will be made publicly available upon acceptance.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 58 of its 79 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

58 of 79 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  8. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  10. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  11. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  12. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
38 more
  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  6. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  11. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  12. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  13. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  14. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  15. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  16. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  17. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  18. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  19. 2016Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Predictioncited by 217
  20. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  21. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  22. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  23. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  24. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  25. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  26. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 162
  27. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  28. 20183D Point Capsule Networkscited by 106
  29. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  30. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  31. 2018Point Cloud GANcited by 79
  32. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75
  33. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  34. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  35. 2020Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learningcited by 68
  36. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  37. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  38. 2018Learning Descriptor Networks for 3D Shape Synthesis and Analysiscited by 56

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 2; 2026: 1.

5 papers.

  1. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  2. 2025Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learningcited by 5
  3. 2023Point Clouds Are Specialized Images: A Knowledge Transfer Approach for 3D Understandingcited by 3
  4. 2025Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformerscited by 2
  5. 2026x2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Spacecited by 0