# Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training

arXiv: https://arxiv.org/abs/2302.14007 · HTML: https://mlsanity.com/paper/2302.14007/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 79 references that are in the map.
- First posted on arXiv 27 Feb 2023.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [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)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (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)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [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)

## Built on by (most cited first, 30 of 52)

- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners](https://mlsanity.com/paper/2303.02151/) (2023)
- [Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement](https://mlsanity.com/paper/2304.01195/) (2023)
- [ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance](https://mlsanity.com/paper/2303.16894/) (2023)
- [Point Cloud Pre-training with Diffusion Models](https://mlsanity.com/paper/2311.14960/) (2023)
- [Traj-MAE: Masked Autoencoders for Trajectory Prediction](https://mlsanity.com/paper/2303.06697/) (2023)
- [Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models](https://mlsanity.com/paper/2310.03059/) (2023)
- [Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders](https://mlsanity.com/paper/2312.10726/) (2023)
- [Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis](https://mlsanity.com/paper/2303.08134/) (2023)
- [Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation](https://mlsanity.com/paper/2312.12480/) (2023)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders](https://mlsanity.com/paper/2408.08753/) (2024)
- [Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding](https://mlsanity.com/paper/2404.07989/) (2024)
- [No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation](https://mlsanity.com/paper/2404.04050/) (2024)
- [SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners](https://mlsanity.com/paper/2408.16768/) (2024)
- [Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning](https://mlsanity.com/paper/2407.05862/) (2024)
- [3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V](https://mlsanity.com/paper/2312.09738/) (2023)
- [Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking](https://mlsanity.com/paper/2303.05475/) (2023)
- [LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling](https://mlsanity.com/paper/2405.17149/) (2024)
- [MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition](https://mlsanity.com/paper/2311.18402/) (2023)
- [PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models](https://mlsanity.com/paper/2512.08330/) (2025)
- [PointSea: Point Cloud Completion via Self-structure Augmentation](https://mlsanity.com/paper/2502.17053/) (2025)
- [Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views](https://mlsanity.com/paper/2509.01250/) (2025)
- [Multi-modal Relation Distillation for Unified 3D Representation Learning](https://mlsanity.com/paper/2407.14007/) (2024)
- [Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models](https://mlsanity.com/paper/2605.03438/) (2026)
- [Tri-Efficient Transfer Learning for Point Cloud Videos](https://mlsanity.com/paper/2606.24175/) (2026)
- [Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformers](https://mlsanity.com/paper/2407.13200/) (2024)
- [Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning](https://mlsanity.com/paper/2507.09102/) (2025)

## Abstract (arXiv)

Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision. However, existing MAE-style methods can only learn from the data of a single modality, i.e., either images or point clouds, which neglect the implicit semantic and geometric correlation between 2D and 3D. In this paper, we explore how the 2D modality can benefit 3D masked autoencoding, and propose Joint-MAE, a 2D-3D joint MAE framework for self-supervised 3D point cloud pre-training. Joint-MAE randomly masks an input 3D point cloud and its projected 2D images, and then reconstructs the masked information of the two modalities. For better cross-modal interaction, we construct our JointMAE by two hierarchical 2D-3D embedding modules, a joint encoder, and a joint decoder with modal-shared and model-specific decoders. On top of this, we further introduce two cross-modal strategies to boost the 3D representation learning, which are local-aligned attention mechanisms for 2D-3D semantic cues, and a cross-reconstruction loss for 2D-3D geometric constraints. By our pre-training paradigm, Joint-MAE achieves superior performance on multiple downstream tasks, e.g., 92.4% accuracy for linear SVM on ModelNet40 and 86.07% accuracy on the hardest split of ScanObjectNN.