mlsanityData to 14 Oct 2026

Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud

arXiv 2404.16432 ↗First posted 25 Apr 2024cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in the input space, or the necessity of additional modalities. In order to address these issues, we introduce Point-JEPA, a joint embedding predictive architecture designed specifically for point cloud data. To this end, we introduce a sequencer that orders point cloud patch embeddings to efficiently compute and utilize their proximity based on the indices during target and context selection. The sequencer also allows shared computations of the patch embeddings' proximity between context and target selection, further improving the efficiency. Experimentally, our method achieves competitive results with state-of-the-art methods while avoiding the reconstruction in the input space or additional modality.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 25 Apr 2024.

Builds on

36 of 49 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  11. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
24 more
  1. 2017Decoupled Weight Decay Regularizationcited by 1,831
  2. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  3. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 727
  4. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  5. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  6. 2020A Survey on Contrastive Self-supervised Learningcited by 554
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  9. 2021SLIP: Self-supervision meets Language-Image Pre-trainingcited by 436
  10. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  11. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  12. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  13. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  14. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144
  15. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  16. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  17. 20183D Point Capsule Networkscited by 106
  18. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  19. 2023Point Cloud Pre-training with Diffusion Modelscited by 47
  20. 2023Point2Vec for Self-Supervised Representation Learning on Point Cloudscited by 28
  21. 2017Learning Representations and Generative Models for 3D Point Cloudscited by 21
  22. 2022Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learningcited by 19
  23. 2019Self-Supervised Deep Learning on Point Clouds by Reconstructing Spacecited by 6
  24. 2024Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchangecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 5; 2026: 19.

30 papers.

Sort:

By area:

  1. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  2. 2026VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Modelscited by 17
  3. 2024T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computationcited by 12
  4. 2024Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learningcited by 9
  5. 2024LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecastingcited by 8
  6. 2025ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learningcited by 8
  7. 2024Learning Latent Wireless Dynamics from Channel State Informationcited by 7
  8. 2025Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Modelscited by 5
  9. 2026BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learningcited by 4
  10. 2026JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physicscited by 3
  11. 2026Gaussian Joint Embeddings For Self-Supervised Representation Learningcited by 2
  12. 2024Point Cloud Understanding via Attention-Driven Contrastive Learningcited by 1
18 more
  1. 2025Foundry: Distilling 3D Foundation Models for the Edgecited by 1
  2. 2026Point-SRA: Self-Representation Alignment for 3D Representation Learningcited by 1
  3. 2026A Persistent Homology Design Space for 3D Point Cloud Deep Learningcited by 1
  4. 2026Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learningcited by 1
  5. 2026World-as-Graph: Relational World Modeling Through Latent Space Graphscited by 1
  6. 2025PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modelingcited by 0
  7. 2025Label-Efficient Grasp Joint Prediction with Point-JEPAcited by 0
  8. 2026FILTR: Extracting Topological Features from Pretrained 3D Modelscited by 0
  9. 2026TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applicationscited by 0
  10. 2026The JEPA Predictor: A Transferable Operator for Occluded Feature Completioncited by 0
  11. 2026JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimationcited by 0
  12. 2026SR-JEPA: Learning Predictive Latent State in 3D Scenescited by 0
  13. 2026Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecturecited by 0
  14. 2026CellWorld: From Gene-Level Reconstruction to Latent Cell Prediction in Spatial Transcriptomics Foundation Modelscited by 0
  15. 2026Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipatescited by 0
  16. 2026Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videoscited by 0
  17. 2026Polis: 3D Self-Supervision at City Scalecited by 0
  18. 2026I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?cited by 0