ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections Chun-Han Y ao 1 * Amit Raj 2 Wei-Chih Hung 3 Y uanzhen Li2

Specifically, ARTIC3D is built upon a skeleton-based surface representation and is further guided by 2D diffusion priors from Stable Diffusion. First, we enhance the input images with occlusions/truncation via 2D diffusion to obtain cleaner mask estimates and semantic features.