Yuanhao Zhai1, Kevin Lin2, Linjie Li2, Chung-Ching Lin2, Jianfeng Wang2, Zhengyuan Yang2, David Doermann1, Junsong Yuan1, Zicheng Liu3, Lijuan Wang2
1State University of New Yort at Buffalo | 2Microsoft | 3Advanced Micro Devices
European Conference on Computer Vision (ECCV) 2024
TL;DR: Our IDOL enables human-centric joint video-depth generation, which could be rendered into realistic 2.5 videos.
All code and checkpoints will be released soon!