Shih-En Wei

National Taiwan Normal University — Taiwan

Computer Science · Physical Sciences

17h-index16.8kcitations39works0.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(12), Face recognition and analysis(11), Advanced Vision and Imaging(7), Generative Adversarial Networks and Image Synthesis(7), Video Surveillance and Tracking Methods(6)

Publications39 total

A Real-Time Power-Saving Framework for Mobile Camera Applications Based on Machine Learning
IEEE Access·2026Open Access
Rewind: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning
2025· 1 cited
REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning
arXiv (Cornell University)·2025Open Access
Content-based Power-saving Design for Augmented Reality Applications on Mobile Devices
2024
Fast Registration of Photorealistic Avatars for VR Facial Animation
arXiv (Cornell University)·2024Open Access
Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars
2024
Exploiting Machine-learning Prediction for Enabling Real-time Pixel-scaling Techniques in Mobile Camera Applications
2023· 1 cited
Drivable Volumetric Avatars using Texel-Aligned Features
arXiv (Cornell University)·2022· 1 citedOpen Access
Drivable Volumetric Avatars using Texel-Aligned Features
2022· 57 citedOpen Access
Authentic volumetric avatars from a phone scan
ACM Transactions on Graphics·2022· 109 citedOpen Access
Robust Egocentric Photo-realistic Facial Expression Transfer for Virtual Reality
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 13 cited
LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space
arXiv (Cornell University)·2022Open Access
LiP-Flow: Learning Inference-Time Priors for Codec Avatars via Normalizing Flows in Latent Space
Lecture notes in computer science·2022
Deep relightable appearance models for animatable faces
ACM Transactions on Graphics·2021· 72 cited
Driving-signal aware full-body avatars
ACM Transactions on Graphics·2021· 7 cited
Deep relightable appearance models for animatable faces
ACM Transactions on Graphics·2021· 2 citedOpen Access
SimPoE: Simulated Character Control for 3D Human Pose Estimation
2021· 123 cited
Robust Egocentric Photo-realistic Facial Expression Transfer for Virtual Reality
arXiv (Cornell University)·2021Open Access
SimPoE: Simulated Character Control for 3D Human Pose Estimation
arXiv (Cornell University)·2021· 2 citedOpen Access
The eyes have it
ACM Transactions on Graphics·2020· 52 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Jason Saragih(20), Yaser Sheikh(16), Tomas Simon(15), Stephen Lombardi(7), Shunsuke Saito(7), Zhe Cao(5), Shoou-I Yu(5), Hung‐Yun Hsieh(5), Timur Bagautdinov(4), Fabián Prada(4), Te-Li Wang(4), Shaojie Bai(4), Xuanyi Dong(3), Xinshuo Weng(3), Yi Yang(3), Adam W. Harley(3), Hernán Badino(3), Danielle Belko(3), Chenglei Wu(3), Te-Li Wang(3)