Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation

1 code implementation • 9 Aug 2023 • Takahiko Furuya, Zhoujie Chen, Ryutarou Ohbuchi, Zhenzhong Kuang

To facilitate the learning of accurate features, we propose to combine multi-crop and cut-mix data augmentation techniques to diversify 3D point sets for training.

Data Augmentation Self-Supervised Learning