Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

Zekun Qi, Runpei Dong, Guofan Fan, Zheng Ge, Xiangyu Zhang, Kaisheng Ma, Li Yi

Abstract: Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achie...