Pre-training by numerous image data has become de-facto for robust 2D
representations. In contrast, due to the expensive data acquisition and
annotation, a paucity of large-scale 3D datasets severely hinders the learning
for high-quality 3D features. In this paper, we propose an alternative to
obtain superior 3D representations from 2D pre-trained models via
Image-to-Point Masked Autoencoders, named as I2P-MAE. By self-supervised
pre-training, we leverage the well learned 2D knowledge to guide 3D masked
autoencoding, which reconstructs the masked point tokens with an
encoder-decoder architecture. Specifically, we first utilize off-the-shelf 2D
models to extract the multi-view visual features of the input point cloud, and
then conduct two types of image-to-point learning schemes on top. For one, we
introduce a 2D-guided masking strategy that maintains semantically important
point tokens to be visible for the encoder. Compared to random masking, the
network can better concentrate on significant 3D structures and recover the
masked tokens from key spatial cues. For another, we enforce these visible
tokens to reconstruct the corresponding multi-view 2D features after the
decoder. This enables the network to effectively inherit high-level 2D
semantics learned from rich image data for discriminative 3D modeling. Aided by
our image-to-point pre-training, the frozen I2P-MAE, without any fine-tuning,
achieves 93.4% accuracy for linear SVM on ModelNet40, competitive to the fully
trained results of existing methods. By further fine-tuning on on
ScanObjectNN's hardest split, I2P-MAE attains the state-of-the-art 90.11%
accuracy, +3.68% to the second-best, demonstrating superior transferable
capacity. Code will be available at this https URL.

利用自监督的预训练，我们通过 Image-to-Point Masked Autoencoders（I2P-MAE）从 2D 预训练模型中获取优秀的 3D 表示，其中我们引入了两种图像到点的学习方案：一种是引入 2D 引导遮罩策略，另一种是通过可见的点重构相应的多视角 2D 特征；与现有方法的完全训练结果相当的冻结 I2P-MAE 在 ModelNet40 上实现了 93.4％的线性 SVM 准确性，在进一步在 ScanObjectNN 的最困难的分割上进行微调后，I2P-MAE 达到了 90.11％的最新技术水平，比第二好的方法高 3.68％，展示出优秀的可转移能力。