IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation.

Yuanhao Zhai, Kevin Lin, Linjie Li, Chung-Ching Lin, Jianfeng Wang, Zhengyuan Yang, David S. Doermann, Junsong Yuan, Zicheng Liu, Lijuan Wang

Browse the full ECCV paper archive.