collaborators

6 papers

cs.CV2026

GRAPE: Graduated Routing for Articulated Portrait mesh Estimation

Yunfei Liu, Lijian Lin, Ye Zhu +1

Articulated portrait mesh estimation is fundamental to 3D understanding, avatar generation, and immersive interaction. Existing approaches primarily rely on 3D Morphable Models (3D…

cs.CV2026

PEAR: Pixel-aligned Expressive humAn mesh Recovery

Jiahao Wu, Yunfei Liu, Lijian Lin +4

Reconstructing detailed 3D human meshes from a single in-the-wild image remains a fundamental challenge in computer vision. Existing SMPLX-based methods often suffer from slow infe…

cs.CV2025

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Dongbin Zhang, Yunfei Liu, Lijian Lin +5

Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application…

cs.CV2025

HRAvatar: High-Quality and Relightable Gaussian Head Avatar

Dongbin Zhang, Yunfei Liu, Lijian Lin +5

Reconstructing animatable and high-quality 3D head avatars from monocular videos, especially with realistic relighting, is a valuable task. However, the limited information from si…

cs.CV2025

TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction

Yunfei Liu, Lei Zhu, Lijian Lin +3

3D facial reconstruction from a single in-the-wild image is a crucial task in human-centered computer vision tasks. While existing methods can recover accurate facial shapes, there…

cs.CV2025

Identity-Preserving Video Dubbing Using Motion Warping

Runzhen Liu, Qinjie Lin, Yunfei Liu +5

Video dubbing aims to synthesize realistic, lip-synced videos from a reference video and a driving audio signal. Although existing methods can accurately generate mouth shapes driv…