Shangchen Zhou
Research Assistant Professor at Nanyang Technological University Singapore
Singapore
Summary
🤩
Rockstar🎓
Top SchoolShangchen Zhou is a Research Assistant Professor at MMLab, Nanyang Technological University, bringing nine years of experience in computer vision and machine learning research. He completed a PhD in Computer Science at NTU and has progressed through roles from Research Associate to Research Fellow and now faculty, focusing on practical, production-ready vision systems. His contributions to the popular CodeFormer project highlight hands-on engineering in robust blind face restoration, including face detection updates, Real-ESRGAN upsampling compatibility across GPUs/CPU, and video/audio processing features. Based in Singapore, he blends academic rigor with engineering pragmatism to move models from research prototypes to usable tools. Colleagues value his knack for improving cross-hardware reliability and end-to-end media pipelines—skills that often go unremarked in purely academic CVs.
9 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Nanyang Technological University Singapore
Chinese, English
Github Skills (5)
video-processing10
face-detection10
computer-vision10
pytorch10
python10
Programming languages (2)
Github contributions (5)
sczhou/CodeFormer
Jun 2022 - Jan 2023
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Role in this project:
ML Engineer
ML EngineerContributions:1 release, 56 commits, 23 PRs in 7 months
Contributions summary:Shangchen primarily contributed to the face restoration and enhancement project, specifically updating and integrating face detection capabilities. This includes modifications to the face detector, and enhancements to the Real-ESRGAN upsampling process to ensure compatibility across various GPU configurations and CPU execution. The user also worked on video processing, adding features to handle video input and incorporating audio for enhanced video outputs.
codebookpytorchblindrestorationneurips
sczhou/DAVANet
May 2019 - Apr 2021
[CVPR 2019, Oral] DAVANet: Stereo Deblurring with View Aggregation
Contributions:1 review, 15 commits, 2 PRs in 1 year 11 months
pytorchaggregationstereodeblurringstereo-deblurring
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.