Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors (original) (raw)

Zhengfei Kuang1, Tianyuan Zhang2, Kai Zhang3, Hao Tan3, Sai Bi3, Yiwei Hu3, Zexiang Xu3, Milos Hasan3, Gordon Wetzstein1, Fujun Luan3
1 Stanford University 2 Massachusetts Institute of Technology 3 Adobe Research
CVPR 2025

arXiv

Smooth and Consistent Video Depth and Normal Generation without Annotated Video Data.

(This webpage contains a lot of videos. We suggest using Chrome or Edge for the best experience)