Multi-View Representation is What You Need for Point-Cloud Pre-Training

arXiv:2306.02558v3 Announce Type: replace
Abstract: A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud pre-training that learns 3D representations by leveraging pre-trained 2D networks. Different from the popular practice of predicting 2D features first and then obtaining 3D features through dimensionality lifting, our approach directly uses a 3D network for feature …

abstract arxiv challenge cloud cs.cv data domain fundamental gap massive novel paper point-cloud pre-training representation training type view