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

arXiv: https://arxiv.org/abs/2404.16432 · HTML: https://mlsanity.com/paper/2404.16432/

## 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 (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://mlsanity.com/paper/2012.09165/) (2020)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders](https://mlsanity.com/paper/2212.06785/) (2022)
- [Self-supervised Learning in Remote Sensing: A Review](https://mlsanity.com/paper/2206.13188/) (2022)
- [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://mlsanity.com/paper/2305.11487/) (2023)
- [3D Point Capsule Networks](https://mlsanity.com/paper/1812.10775/) (2018)
- [Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2107.01886/) (2021)

## Built on by (most cited first, 30 of 30)

- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models](https://mlsanity.com/paper/2601.14354/) (2026)
- [T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computation](https://mlsanity.com/paper/2406.12913/) (2024)
- [Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning](https://mlsanity.com/paper/2412.20790/) (2024)
- [LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting](https://mlsanity.com/paper/2405.10093/) (2024)
- [ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning](https://mlsanity.com/paper/2501.14622/) (2025)
- [Learning Latent Wireless Dynamics from Channel State Information](https://mlsanity.com/paper/2409.10045/) (2024)
- [Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2512.15885/) (2025)
- [BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning](https://mlsanity.com/paper/2603.00049/) (2026)
- [JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics](https://mlsanity.com/paper/2606.14813/) (2026)
- [Gaussian Joint Embeddings For Self-Supervised Representation Learning](https://mlsanity.com/paper/2603.26799/) (2026)
- [Point Cloud Understanding via Attention-Driven Contrastive Learning](https://mlsanity.com/paper/2411.14744/) (2024)
- [Foundry: Distilling 3D Foundation Models for the Edge](https://mlsanity.com/paper/2511.20721/) (2025)
- [Point-SRA: Self-Representation Alignment for 3D Representation Learning](https://mlsanity.com/paper/2601.01746/) (2026)
- [A Persistent Homology Design Space for 3D Point Cloud Deep Learning](https://mlsanity.com/paper/2604.04299/) (2026)
- [Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning](https://mlsanity.com/paper/2607.00514/) (2026)
- [World-as-Graph: Relational World Modeling Through Latent Space Graphs](https://mlsanity.com/paper/2609.38927/) (2026)
- [PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling](https://mlsanity.com/paper/2507.04801/) (2025)
- [Label-Efficient Grasp Joint Prediction with Point-JEPA](https://mlsanity.com/paper/2509.13349/) (2025)
- [FILTR: Extracting Topological Features from Pretrained 3D Models](https://mlsanity.com/paper/2604.22334/) (2026)
- [TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications](https://mlsanity.com/paper/2606.01520/) (2026)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)
- [JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2607.26600/) (2026)
- [SR-JEPA: Learning Predictive Latent State in 3D Scenes](https://mlsanity.com/paper/2608.05774/) (2026)
- [Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2608.06062/) (2026)
- [CellWorld: From Gene-Level Reconstruction to Latent Cell Prediction in Spatial Transcriptomics Foundation Models](https://mlsanity.com/paper/2608.06659/) (2026)
- [Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates](https://mlsanity.com/paper/2608.21160/) (2026)
- [Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videos](https://mlsanity.com/paper/2608.24093/) (2026)
- [Polis: 3D Self-Supervision at City Scale](https://mlsanity.com/paper/2608.29426/) (2026)
- [I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?](https://mlsanity.com/paper/2609.31161/) (2026)

## 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.