Fujun Luan
Senior Machine Learning Researcher at Apple
Sunnyvale, California, United States
Summary
🤩
Rockstar🎓
Top SchoolFujun Luan is a Senior Machine Learning Researcher with 11 years of experience building foundation models and neural rendering systems, currently working on AI/ML at Apple in Sunnyvale. He holds a PhD from Cornell and has driven research-to-product work at Adobe, including large-scale video foundation models with 3D camera control and shipped text-to-3D features in the Seashell Viewer. His background blends forward/inverse rendering, neural relighting, and synthetic-data pipelines, and he’s authored numerous top-tier publications and patents while integrating NeRF and neural assets into production renderers. Early contributions include CUDA-optimized image harmonization code (Deep Painterly Harmonization) and differentiable raytracing for multi-view reconstruction, highlighting a rare mix of low-level engineering and high-level model research. Known for translating cutting-edge graphics research into scalable production systems, he often presents results directly to engineering and executive audiences.
11 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at Cornell UniversityBachelor’s Degree Computer Science, Bachelor’s Degree Computer Science at Tsinghua University
English, Chinese
Github Skills (9)
cuda10
lua10
computer-vision10
pytorch10
image-processing10
machine-learning9
deep-learning9
faster-rcnn8
mask-rcnn8
Programming languages (6)
Github contributions (5)
luanfujun/deep-painterly-harmonization
Apr 2018 - Apr 2018
Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189
Role in this project:
ML Engineer
ML EngineerContributions:78 commits, 1 PR, 32 pushes in 16 days
Contributions summary:Fujun's contributions primarily focused on modifying and extending the existing codebase for deep painterly harmonization. They added new CUDA kernels, including histogram calculation and remapping, crucial for image processing. Further contributions included updates to the Lua scripts used for the project, adding patchmatch functionality. These modifications suggest an effort to enhance the model's performance and refine the image harmonization process.
pytorcharxivabsdeep-learningharmonization
luanfujun/luanfujun.github.io
Jan 2022 - Aug 2024
Contributions:12 PRs, 138 pushes, 6 branches in 2 years 7 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.