Yan Zhou

Yan Zhou

Auto-generated profile, based on publicly available information

Yan Zhou

Kuaishou Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2026 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
XZXukun Zhou
Xukun Zhou
FLFengxin Li
Fengxin Li
MCMing Chen
Ming Chen
YZYan Zhou
Yan Zhou
PWPengfei Wan
Pengfei Wan
XLXuelong Li
Xuelong Li
Audio-driven human gesture synthesis is a crucial task with broad applications in virtual avatars, human-computer interaction, and creative content generation. Despite notable progress, existing methods often produce coarse gestures, lack expressiveness, and fail to fully align with audio semantics. To address these challenges, we propose ExGes, a novel retrieval-enhanced diffusion framework with three key designs: (1) a Motion Base Construction, which builds a gesture library from the training dataset; (2) a Motion Retrieval Module, employing contrastive learning and momentum distillation for retrieving fine-grained reference poses; and (3) a Precise Control Module, integrating partial masking and stochastic masking to enable flexible and fine-grained control. Experimental evaluations on BEAT2 demonstrate that ExGes reduces Fréchet Gesture Distance by 4.55%and improves motion diversity by 5.3% over EMAGE, with user studies revealing a 71.3% preference for its naturalness and semantic relevance.

26 October 2025
Verified
Conference Paper
Open access
NGNan Gao
Nan Gao
YBYihua Bao
Yihua Bao
DWDongdong Weng
Dongdong Weng
JZJiayi Zhao
Jiayi Zhao
JLJia Li
Jia Li
PWPengfei Wan
Pengfei Wan

26 October 2023
Verified
Conference Paper
Open access
MZMingrui Zhang
Mingrui Zhang
MCMing Chen
Ming Chen
YZYan Zhou
Yan Zhou
LCLi Chen
Li Chen
WJWeihua Jian
Weihua Jian
PWPengfei Wan
Pengfei Wan
Human scene interaction (HSI) aims to understand and accommodate the various ways humans interact with their environment. However, existing works typically struggle to produce high-precision contact estimation for understanding these interactions and lack sufficient fine-grained semantics to adapt to the complexities of diverse characters and scenes, resulting in unnatural and inaccurate interacting motions. In this paper, we present a novel approach to automatic human scene interaction that effectively recovers the human body mesh and high-precision contact information, subsequently enabling adaptation to different environments. Our main contributions include the proposal of a contact estimation framework that leverages semantic features from 2D images and 3D model recovered with inverse kinematics to guide the learning of vertex-level human scene contact (HSC) estimation. For motion adaptation, we propose an enhanced Laplacian semantics descriptor combined with kinematic constraints, enabling precise retargeting between variously sized human models and distinct 3D scenes. Through extensive experiments, we demonstrate our method's superiority against state-of-the-art approaches and showcase the results of the automatic human scene interaction process.

9 November 2026
Verified
Conference Paper
Open access
XWXinyu Wang
Xinyu Wang
HSHuafeng Shi
Huafeng Shi
ZLZian Li
Zian Li
ZYZhou Yan
Zhou Yan
XLXiaoqiang Liu
Xiaoqiang Liu
PWPengfei Wan
Pengfei Wan