About me

I am a fourth year Ph.D student, working in the USC Graphics Lab with Prof. Hao Li. Before that I obtained my bachelor degree in Yao Class (Theoretical Computer Science), Tsinghua University.

My formal Chinese name is Lingyu Wei (魏凌宇), but most of the time people cannot pronounce it properly. Therefore, you are very welcome to call me Cosimo :-)

Research Interests

Computer graphics, Machine learning (usually deep learning), Basic algorithms on geometry and mathematics.


Face norm

Deep Face Normalization


Koki Nagano, Huiwen Luo, Zejian Wang, Jaewoo Seo, Jun Xing, Liwen Hu, Lingyu Wei, Hao Li

[ Paper 10MB ] [ Video YouTube ]


paGAN: Real-time Avatars Using Dynamic Textures


Koki Nagano, Jaewoo Seo, Jun Xing, Lingyu Wei, Zimo Li, Shunsuke Saito, Aviral Agarwal, Jens Fursund, Hao Li

[ Paper 39MB ] [ Video YouTube ]

Hair render

Real-Time Hair Rendering using Sequential Adversarial Networks

ECCV 2018

Lingyu Wei, Liwen Hu, Vladimir Kim, Ersin Yumer, Hao Li

[ Paper 20MB ] [ Video YouTube ] [ Poster 18MB ]

Oneshot avatar

Avatar Digitization From A Single Image For Real-time Rendering


Liwen Hu*, Shunsuke Saito*, Lingyu Wei*, Koki Nagano, Jaewoo Seo, Jens Fursund, Iman Sadeghi, Carrie Sun, Yen-Chun Chen, Hao Li

[ Paper 23MB ] [ Video YouTube ]

Face texture

Photorealistic Facial Texture Inference Using Deep Neural Networks

CVPR 2017, spotlight presentation

Shunsuke Saito*, Lingyu Wei*, Liwen Hu, Koki Nagano, Hao Li

[ Project ] [ Paper 9MB ] [ Poster 3MB ] [ Video YouTube ]


Capturing Dynamic Textured Surfaces Of Moving Targets

ECCV 2016, spotlight presentation

Ruizhe Wang, Lingyu Wei, Etienne Vouga, Qixing Huang, Duygu Ceylan, Gerard Medioni, Hao Li

[ Project ] [ Paper 6MB ] [ Poster 2MB ] [ Video 35MB ]

Dense descriptor

Dense Human Body Correspondence Using Convolutional Networks

CVPR 2016, oral presentation

Lingyu Wei, Qixing Huang, Duygu Ceylan, Etienne Vouga, Hao Li

[ Project ] [ Paper 3MB ] [ Video 31MB ] [ Yobi3D dataset 1MB ]

Head mounted intel cam

Facial Performance Sensing Head-Mounted Display


Hao Li*, Laura Trutoiu*, Kyle Olszewski*, Lingyu Wei*, Tristan Trutna, Pei-Lun Hsieh, Aaron Nicholls, Chongyang Ma

[ Project ] [ Paper 7MB ] [ Video 212MB ]


Support Substructures: Support-Induced Part-Level Structural Representation

IEEE transactions on Visualization and Computer Graphics (TVCG), 2015

Shi-Sheng Huang, Hongbo Fu, Ling-Yu Wei, Shi-Min Hu

[ Paper 2MB ]


Rendering chamfering structures of sharp edges

The Visual Computer, 2014

Ling-Yu Wei, Kan-Le Shi, Jun-Hai Yong

[ Paper 1MB ] [ Dropbox (Code included) ]


A Faster Triangle to Triangle Intersection Test Algorithm

Computer Animation and Virtual Worlds, 2013

Ling-Yu Wei

[ Paper CAVW ] [ Code unoptimized ]