# 3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning

arXiv: https://arxiv.org/abs/2409.15803 · HTML: https://mlsanity.com/paper/2409.15803/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Builds on (most cited first, 30 of 33)

- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders](https://mlsanity.com/paper/2206.09900/) (2022)
- [The Hidden Uniform Cluster Prior in Self-Supervised Learning](https://mlsanity.com/paper/2210.07277/) (2022)
- [MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features](https://mlsanity.com/paper/2307.12698/) (2023)
- [Point2Vec for Self-Supervised Representation Learning on Point Clouds](https://mlsanity.com/paper/2303.16570/) (2023)
- [Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning](https://mlsanity.com/paper/2202.04241/) (2022)
- [3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.14084/) (2022)
- [UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving](https://mlsanity.com/paper/2305.18829/) (2023)

## Built on by (most cited first, 14 of 14)

- [CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images](https://mlsanity.com/paper/2511.18424/) (2025)
- [AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling](https://mlsanity.com/paper/2605.05586/) (2026)
- [SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors](https://mlsanity.com/paper/2608.04060/) (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)
- [TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications](https://mlsanity.com/paper/2606.01520/) (2026)
- [Synesthesia via Direct Latent Augmentation:Bypassing the Decode-Encode Loop for Cross-Modal Distillation](https://mlsanity.com/paper/2606.08336/) (2026)
- [Neural Voxel Dynamics: Learning Volumetric Feature Advection for 3D Physics in V-JEPA Latent Space](https://mlsanity.com/paper/2606.26410/) (2026)
- [SR-JEPA: Learning Predictive Latent State in 3D Scenes](https://mlsanity.com/paper/2608.05774/) (2026)
- [Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates](https://mlsanity.com/paper/2608.21160/) (2026)
- [Polis: 3D Self-Supervision at City Scale](https://mlsanity.com/paper/2608.29426/) (2026)
- [GeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human Videos](https://mlsanity.com/paper/2609.17099/) (2026)
- [Mask-Aware Execution for Efficient JEPA Training](https://mlsanity.com/paper/2609.22674/) (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)

Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable to all downstream tasks, and the latter indiscriminately reconstructs masked regions, resulting in irrelevant details being saved in the representation space. To solve the problem above, we introduce 3D-JEPA, a novel non-generative 3D SSRL framework. Specifically, we propose a multi-block sampling strategy that produces a sufficiently informative context block and several representative target blocks. We present the context-aware decoder to enhance the reconstruction of the target blocks. Concretely, the context information is fed to the decoder continuously, facilitating the encoder in learning semantic modeling rather than memorizing the context information related to target blocks. Overall, 3D-JEPA predicts the representation of target blocks from a context block using the encoder and context-aware decoder architecture. Various downstream tasks on different datasets demonstrate 3D-JEPA's effectiveness and efficiency, achieving higher accuracy with fewer pretraining epochs, e.g., 88.65% accuracy on PB_T50_RS with 150 pretraining epochs.