# CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images

arXiv: https://arxiv.org/abs/2511.18424 · HTML: https://mlsanity.com/paper/2511.18424/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 86 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Builds on (most cited first, 30 of 58)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [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)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Train faster, generalize better: Stability of stochastic gradient descent](https://mlsanity.com/paper/1509.01240/) (2015)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [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)
- [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)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)

## Built on by (most cited first, 4 of 4)

- [AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling](https://mlsanity.com/paper/2605.05586/) (2026)
- [Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning](https://mlsanity.com/paper/2607.00514/) (2026)
- [Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats](https://mlsanity.com/paper/2608.15651/) (2026)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)

## Abstract (arXiv)

Image-to-point cross-modal learning has emerged to address the scarcity of large-scale 3D datasets in 3D representation learning. However, current methods that leverage 2D data often result in large, slow-to-train models, making them computationally expensive and difficult to deploy in resource-constrained environments. The architecture design of such models is therefore critical, determining their performance, memory footprint, and compute efficiency. The Joint-embedding Predictive Architecture (JEPA) has gained wide popularity in self-supervised learning for its simplicity and efficiency, but has been under-explored in cross-modal settings, partly due to the misconception that masking is intrinsic to JEPA. In this light, we propose CrossJEPA, a simple Cross-modal Joint Embedding Predictive Architecture that harnesses the knowledge of an image foundation model and trains a predictor to infer embeddings of specific rendered 2D views from corresponding 3D point clouds, thereby introducing a JEPA-style pretraining strategy beyond masking. By conditioning the predictor on cross-domain projection information, CrossJEPA purifies the supervision signal from semantics exclusive to the target domain. We further exploit the frozen teacher design with a one-time target embedding caching mechanism, yielding amortized efficiency. CrossJEPA achieves a new state-of-the-art in linear probing on the synthetic ModelNet40 (94.2%) and the real-world ScanObjectNN (88.3%) benchmarks, using only 14.1M pretraining parameters (8.5M in the point encoder), and about 6 pretraining hours on a standard single GPU. These results position CrossJEPA as a performant, memory-efficient, and fast-to-train framework for 3D representation learning via knowledge distillation. We analyze CrossJEPA intuitively, theoretically, and empirically, and extensively ablate our design choices. Code will be made available.