Xiaoshuai Zhang*

ConDense: Consistent 2D-3D Pre-training for Dense and Sparse Features from Multi-View Images

"To advance the state of the art in the creation of 3D foundation models, this paper introduces the framework for 3D pre-training utilizing existing pre-trained 2D networks and large-scale multi-view datasets. We propose a novel 2D-3D joint training scheme to extract co-embedded 2D and 3D features i…