Chen-hsuan Lin
Staff Research Scientist & Research Manager at NVIDIA
California, United States
Summary
🤩
Rockstar🎓
Top SchoolChen-hsuan Lin is a Staff Research Scientist and Research Manager at NVIDIA Cosmos Lab with 11 years of experience bridging robotics, computer vision, and machine learning research. He earned a PhD in Robotics from Carnegie Mellon and has progressed through research roles at NVIDIA after internships at Facebook AI and Adobe, bringing both deep academic rigor and production-focused engineering to industrial research. His work includes implementing and refining notable projects such as BARF (Bundle-Adjusting Neural Radiance Fields), contributing practical code for novel view synthesis, camera pose optimization, and test-time photometric refinement. Based in California, he leads teams to translate state-of-the-art research into robust systems, while still contributing hands-on to high-impact open-source repositories. A detail that sets him apart is his ability to combine Procrustes-aligned pose validation and photometric optimization in research code, reflecting a rare mix of geometric insight and ML engineering.
11 years of coding experience
11 years of employment as a software developer
Bachelor of Science (B.S.), Electrical Engineering, Bachelor of Science (B.S.), Electrical Engineering at National Taiwan UniversityDoctor of Philosophy (Ph.D.), Robotics, Doctor of Philosophy (Ph.D.), Robotics at Carnegie Mellon University
Github Skills (11)
computer-vision10
pytorch10
eval10
trainings10
bundle10
bundler10
python10
evaluation10
modeling10
image-processing9
ffmpeg8
Programming languages (2)
Github contributions (5)
chenhsuanlin/bundle-adjusting-NeRF
Jul 2021 - Apr 2022
BARF: Bundle-Adjusting Neural Radiance Fields 🤮 (ICCV 2021 oral)
Role in this project:
ML Engineer
ML EngineerContributions:11 commits, 4 PRs, 9 pushes in 9 months
Contributions summary:Chen-hsuan implemented and refined core components related to Bundle-Adjusting Neural Radiance Fields (BARF), as evidenced by the "release" commits that introduced and updated the `nerf.py` and `planar.py` files. The changes include model definition, training, and evaluation procedures for novel view synthesis tasks. Furthermore, the user incorporated updates to handle test-time photometric optimization and improve the validation process using Procrustes alignment for camera poses.
pytorchiccvdeep-learningbundleneural-radiance-fields
chenhsuanlin/spatial-transformer-GAN
Mar 2018 - Apr 2019
Contributions:24 commits, 15 pushes, 46 comments in 1 year 1 month
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.