Boosting3D: High-Fidelity Image-to-3D by Boosting 2D Diffusion Prior to 3D Prior with Progressive Learning

Kai Yu, Jinlin Liu, Mengyang Feng +2

We present Boosting3D, a multi-stage single image-to-3D generation method that can robustly generate reasonable 3D objects in different data domains. The point of this work is to s…