Chenyi Kuang — accepted AI-conference papers

2023

Biomechanics-Guided Facial Action Unit Detection Through Force Modeling

Zijun Cui, Chenyi Kuang, Tian Gao, Kartik Talamadupula, Qiang Ji

CVPR 2023poster

Existing AU detection algorithms are mainly based on appearance information extracted from 2D images, and well-established facial biomechanics that governs 3D facial skin deformation is rarely considered. In this paper, we propose a biomechanics-guided AU detection approach, where facial muscle acti…

Cited by 25 Source ↗PDF ↗Scholar ↗

2022

AU-Aware 3D Face Reconstruction through Personalized AU-Specific Blendshape Learning

Chenyi Kuang, Zijun Cui, Jeffrey O. Kephart, Qiang Ji

ECCV 2022poster

"3D face reconstruction and facial action unit (AU) detection have emerged as interesting and challenging tasks in recent years, but are rarely performed in tandem. Image-based 3D face reconstruction, which can represent a dense space of facial motions, is typically accomplished by estimating identi…

Cited by 9 Source ↗PDF ↗Scholar ↗