mlsanityData to 7 Oct 2026

PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models

arXiv 2512.08330 ↗First posted 9 Dec 2025cs.CVcited by 11

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Self-supervised representation learning has shown significant improvement in Natural Language Processing and 2D Computer Vision. However, existing methods face difficulties in representing 3D data because of its unordered and uneven density. Through an in-depth analysis of mainstream contrastive and generative approaches, we find that contrastive models tend to suffer from overfitting, while 3D Mask Autoencoders struggle to handle unordered point clouds. This motivates us to learn 3D representations by sharing the merits of diffusion and contrast models, which is non-trivial due to the pattern difference between the two paradigms. In this paper, we propose textitPointDico, a novel model that seamlessly integrates these methods. textitPointDico learns from both denoising generative modeling and cross-modal contrastive learning through knowledge distillation, where the diffusion model serves as a guide for the contrastive model. We introduce a hierarchical pyramid conditional generator for multi-scale geometric feature extraction and employ a dual-channel design to effectively integrate local and global contextual information. textitPointDico achieves a new state-of-the-art in 3D representation learning, textite.g., 94.32% accuracy on ScanObjectNN, 86.5% Inst. mIoU on ShapeNetPart.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 36 of its 42 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

36 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Point Cloud Pre-training with Diffusion Models25 Nov
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  11. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
22 more
  1. 2022Video Diffusion Modelscited by 2,280
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 2020PCT: Point cloud transformercited by 730
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  6. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  7. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  8. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  9. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  10. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  11. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  12. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  13. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  14. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 159
  15. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  16. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  17. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  18. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  19. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  20. 2023Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-trainingcited by 52
  21. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  22. 2024PCP-MAE: Learning to Predict Centers for Point Masked Autoencoderscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learningcited by 10
  2. 2026Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Modelscited by 6
  3. 2026Diffusion Masked Pretraining for Dynamic Point Cloudcited by 6
  4. 2026Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark Datasetcited by 5
  5. 2026Tri-Efficient Transfer Learning for Point Cloud Videoscited by 5
  6. 2026Momentum Memory for Knowledge Distillation in Computational Pathologycited by 4
  7. 2026GaussFusion: Towards Multimodal 3D Gaussian Pretrainingcited by 2
  8. 2026Parameter-Efficient Fine-Tuning for Spiking Point Cloud Modelscited by 2
  9. 2026Learnable Instance Attention Filtering for Adaptive Detector Distillationcited by 0
  10. 2026Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generationcited by 0
  11. 2026Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
  2. 2023GECCO: Geometrically-Conditioned Point Diffusion Models
  3. 2024DC3DO: Diffusion Classifier for 3D Objects
  4. 2025Guided and Unguided Conditional Diffusion Mechanisms for Structured and Semantically-Aware 3D Point Cloud Generation
  5. 2025CL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point Clouds
  6. 2023CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data
  7. 2026Probing Diffusion Denoising Dynamics for Contrastive Representation Learning
  8. 2023Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data