Unsupervised Point Cloud Pre-Training via Occlusion Completion

1 code implementation • ICCV 2021 • Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby, Matthew J. Kusner

We find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks.

3D Point Cloud Linear Classification Few-Shot 3D Point Cloud Classification +5