| office: |
Campus E1 4,
Room 214 Saarland Informatics Campus 66123 Saarbrücken Germany |
|---|---|
| email: |
ziyangfu@mpi-inf.mpg.de |
| phone: | +49 15229252314 |
I am a first-year Ph.D. student at the Max Planck Institute for Informatics, advised by Dr. Thomas Leimkuehler and Prof. Christian Theobalt, and co-advised by Prof. Ayush Tewari (University of Cambridge).
I started as a rendering guy. Then came the GenAI wave — and it took me two years to fully convert into a true believer in scaling laws. However, I believe data is fundamentally limited, and the industry people will eventually hit a wall. When that day comes, two questions will matter most: Why can it generalize? and How can it generalize? Understanding and building more controllable generative models is what I find most compelling right now. And since I have a deep love for beautiful visual effects, let us start with images and videos.
![]() |
HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
Zimo Wang*, Cheng Wang*, Taiki Yoshino, Sirui Tao, Ziyang Fu, Tzu-Mao Li
*equal contribution Conference on Computer Vision and Pattern Recognition (CVPR), 2025, Highlight [project page] |
![]() |
BSDF Importance Sampling using a Diffusion Model Ziyang Fu, Yash Belhe, Haolin Lu, Liwen Wu, Bing Xu, Tzu-Mao Li SIGGRAPH Asia 2024 (Conference Track Full Paper) [project page] |
![]() |
OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
Isabella Liu*, Linghao Chen*, Ziyang Fu, Liwen Wu, Haian Jin, Zhong Li, Chin Ming Ryan Wong, Yi Xu, Ravi Ramamoorthi, Zexiang Xu, Hao Su
*equal contribution NeurIPS 2023 Datasets and Benchmarks [project page] |