Cheng Sun
Research Scientist at NVIDIA
Taipei, Taiwan
Summary
👤
Senior🎓
Top SchoolCheng Sun is a research scientist specializing in 3D reconstruction, computer vision, and deep learning, currently working at NVIDIA and pursuing a PhD at National Tsing Hua University. With 11 years of experience, he blends academic rigor—supervised by notable vision labs—with industry research that produced an ICCV paper on digital twin reconstruction during his tenure at Meta. Cheng contributes to open-source radiance field tooling (e.g., refactoring core logic in the DirectVoxGO repo), demonstrating hands-on expertise in voxel-based NeRF implementations and model engineering. His recent focus on scene modeling and 3D geometry reflects a practical drive to bridge fast reconstruction techniques with real-world capture pipelines. Based in Taipei, he brings both experimental depth and production-oriented back-end skills to multidisciplinary teams. An often-overlooked strength is his dual fluency in research and implementation, enabling rapid iteration from prototype to reproducible code.
11 years of coding experience
1 year of employment as a software developer
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at National Chiao Tung UniversityDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at National Tsing Hua University
Chinese, English, Japanese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (4)
machine-learning10
3d-reconstruction10
python10
pytorch10
Programming languages (6)
Github contributions (5)
sunset1995/DirectVoxGO
Oct 2021 - Jun 2022
Direct voxel grid optimization for fast radiance field reconstruction.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:100 commits, 29 pushes, 33 comments in 8 months
Contributions summary:Cheng refactored and tested core codes within the `lib/dvgo.py` file, a key component of the DirectVoxGO framework. These changes indicate the user's engagement with the underlying implementation of the radiance field reconstruction. The user also added configurations suggesting involvement in model development or experiments. This points to a role focused on both the back-end logic and potentially model-related tasks for the fast radiance field reconstruction.
reconstructionneural-radiance-fieldsoptimizationnerfcvpr2022
sunset1995/ballfight
Jul 2016 - May 2017
Contributions:220 commits, 172 pushes, 9 branches in 10 months
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.