CVPR2025
World-consistent Video Diffusion with Explicit 3D Modeling
Qihang Zhang, Shuangfei Zhai, Miguel Ángel Bautista Martin, Kevin Miao, Alexander Toshev, Joshua M. Susskind, Jiatao Gu
Abstract
Figure 1. WVD predicts 6D videos from an image, unifying various 3D tasks with a single diffusion model.