6 papers
E-React: Towards Emotionally Controlled Synthesis of Human Reactions
Chen Zhu, Buzhen Huang, Zijing Wu +2
Emotion serves as an essential component in daily human interactions. Existing human motion generation frameworks do not consider the impact of emotions, which reduces naturalness…
Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
Buzhen Huang, Chen Li, Chongyang Xu +4
Due to visual ambiguities and inter-person occlusions, existing human pose estimation methods cannot recover plausible close interactions from in-the-wild videos. Even state-of-the…
Generalizable Human Gaussians from Single-View Image
Jinnan Chen, Chen Li, Jianfeng Zhang +4
In this work, we tackle the task of learning 3D human Gaussians from a single image, focusing on recovering detailed appearance and geometry including unobserved regions. We introd…
Synthesizing Physically Plausible Human Motions in 3D Scenes
Liang Pan, Jingbo Wang, Buzhen Huang +4
We present a physics-based character control framework for synthesizing human-scene interactions. Recent advances adopt physics simulation to mitigate artifacts produced by data-dr…
Adapting Human Mesh Recovery with Vision-Language Feedback
Chongyang Xu, Buzhen Huang, Chengfang Zhang +2
Human mesh recovery can be approached using either regression-based or optimization-based methods. Regression models achieve high pose accuracy but struggle with model-to-image ali…
Simultaneously Recovering Multi-Person Meshes and Multi-View Cameras with Human Semantics
Buzhen Huang, Jingyi Ju, Yuan Shu +1
Dynamic multi-person mesh recovery has broad applications in sports broadcasting, virtual reality, and video games. However, current multi-view frameworks rely on a time-consuming…