Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training
This addresses the challenge of limited labeled 3D data for computer vision researchers, though it is incremental as it builds on existing MAE methods by adding cross-modal integration.
The paper tackles the problem of self-supervised pre-training for 3D point clouds by leveraging 2D images, proposing Joint-MAE, a framework that jointly masks and reconstructs both modalities with cross-modal strategies, achieving 92.4% accuracy on ModelNet40 and 86.07% on ScanObjectNN.
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.