6 papers
InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions
Zhenzhi Wang, Jiaqi Yang, Jianwen Jiang +7
End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However, most existing methods could…
TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation
Zhenzhi Wang, Jian Wang, Ke Ma +2
We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While c…
Multi-identity Human Image Animation with Structural Video Diffusion
Zhenzhi Wang, Yixuan Li, Yanhong Zeng +4
Generating human videos from a single image while ensuring high visual quality and precise control is a challenging task, especially in complex scenarios involving multiple individ…
Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussians
Yixuan Li, Xingjian Ran, Linning Xu +6
Buildings are primary components of cities, often featuring repeated elements such as windows and doors. Traditional 3D building asset creation is labor-intensive and requires spec…
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
Zhenzhi Wang, Yixuan Li, Yanhong Zeng +8
Human image animation involves generating videos from a character photo, allowing user control and unlocking the potential for video and movie production. While recent approaches y…
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
Zhenzhi Wang, Jingbo Wang, Yixuan Li +2
Text-conditioned motion synthesis has made remarkable progress with the emergence of diffusion models. However, the majority of these motion diffusion models are primarily designed…