Uni4D: A Unified Self-Supervised Learning Framework for Point

uni4dUni4D is modular and any component can be swapped for other visual foundation model outputs. For custom vdeo depth estimation and dynamic masks, save them inTitle: Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video; Authors: David Yifan Yao, Albert J. Zhai, Shenlong Wang, Abstract summary: We introduce Uni4D, a