2 papers
cs.CV2025
LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation
Biao Guo, Cong Zhou, Fangmin Guo +3
Most of the current top-down multi-person pose estimation lightweight methods are based on multi-branch parallel pure CNN network architecture, which often struggle to capture the…
cs.CV2025
Reconstruction and Reenactment Separated Method for Realistic Gaussian Head
Zhiling Ye, Cong Zhou, Xiubao Zhang +3
In this paper, we explore a reconstruction and reenactment separated framework for 3D Gaussians head, which requires only a single portrait image as input to generate controllable…