Zihan Yu

I am a Research Scientist at Meta Reality Labs. I received my Ph.D. from the School of Information and Computer Science at the University of California, Irvine, where I was advised by Shuang Zhao. Prior to UCI, I obtained my M.S. in Computer Science from Columbia University and my B.Eng. in Software Engineering from Tongji University.

Research: My research focuses on physics-based differentiable rendering and simulations using Monte Carlo method, with the goal of developing efficient solutions for inverse problems involving complex geometries to infer material or geometric properties from physical or simulated measurements.

Experience

Research Scientist @ Meta Reality Labs

2025 - Present

Research Intern @ NVIDIA High-Fidelity Physics Research

Jun 2024 - Sep 2024

Research Intern @ NVIDIA Real-Time Graphics Research

Jul 2023 - May 2024

Research Intern @ Meta Reality Labs, Graphics Research

Jun 2022 - Sep 2022

Publications

Robust Derivative Estimation with Walk on Stars

Zihan Yu , Rohan Sawhney, Bailey Miller, Lifan Wu, and Shuang Zhao

ACM Transactions on Graphics / SIGGRAPH Asia, 2025

PDF Code Website Bib

@article{Yu:2025:Grad-WoSt,
  title = {Robust Derivative Estimation with Walk on Stars},
  author = {Yu, Zihan and Sawhney, Rohan and Miller, Bailey and Wu, Lifan and Zhao, Shuang},
  journal = {ACM Transactions on Graphics / SIGGRAPH Asia},
  volume = {44},
  number = {6},
  year = {2025},
  pages = {253:1--253:16},
}

A Differential Monte Carlo Solver For the Poisson Equation

Zihan Yu , Lifan Wu, Zhiqian Zhou, and Shuang Zhao

In ACM SIGGRAPH 2024 Conference Proceedings, 2024

PDF Supp Code Website Bib

@inproceedings{Yu:2024:Diff-WOS,
  title = {A Differential Monte Carlo Solver For the Poisson Equation},
  author = {Yu, Zihan and Wu, Lifan and Zhou, Zhiqian and Zhao, Shuang},
  booktitle = {ACM SIGGRAPH 2024 Conference Proceedings},
  year = {2024},
}

Efficient Path-Space Differentiable Volume Rendering With Respect To Shapes

Zihan Yu , Cheng Zhang, Olivier Maury, Christophe Hery, Zhao Dong, and Shuang Zhao

In Computer Graphics Forum, 2023

PDF Website Bib

@inproceedings{yu2023efficient,
  title = {Efficient Path-Space Differentiable Volume Rendering With Respect To Shapes},
  author = {Yu, Zihan and Zhang, Cheng and Maury, Olivier and Hery, Christophe and Dong, Zhao and Zhao, Shuang},
  booktitle = {Computer Graphics Forum},
  volume = {42},
  number = {4},
  pages = {e14884},
  year = {2023},
  organization = {Wiley Online Library},
}

Efficient Differentiation of Pixel Reconstruction Filters for Path-Space Differentiable Rendering

Zihan Yu , Cheng Zhang, Derek Nowrouzezahrai, Zhao Dong, and Shuang Zhao

ACM Transactions on Graphics / SIGGRAPH Asia, 2022

PDF Supp Code Website Bib

@article{Yu:2022:Diff-Pixel,
  title = {Efficient Differentiation of Pixel Reconstruction Filters for Path-Space Differentiable Rendering},
  author = {Yu, Zihan and Zhang, Cheng and Nowrouzezahrai, Derek and Dong, Zhao and Zhao, Shuang},
  journal = {ACM Transactions on Graphics / SIGGRAPH Asia},
  volume = {41},
  number = {6},
  year = {2022},
  pages = {191:1--191:16},
}

Efficient Computational Differentiation for Path-Space Differentiable Rendering

Zihan Yu , Cheng Zhang, Derek Nowrouzezahrai, Zhao Dong, and Shuang Zhao

Jan 2022

Technical Report

PDF Bib

@techreport{yu2023computational,
  title = {Efficient Computational Differentiation for Path-Space Differentiable Rendering},
  author = {Yu, Zihan and Zhang, Cheng and Nowrouzezahrai, Derek and Dong, Zhao and Zhao, Shuang},
  year = {2022},
  institution = {University of California, Irvine},
  month = jan,
  type = {Technical Report},
  number = {UCI-TR-2022-01},
  note = {Technical Report}
}

Path-space differentiable rendering of participating media

Cheng Zhang^*, Zihan Yu^* , and Shuang Zhao

ACM Transactions on Graphics / SIGGRAPH, Jan 2021

PDF Supp Code Website Bib

@article{zhang2021path,
  title = {Path-space differentiable rendering of participating media},
  author = {Zhang, Cheng and Yu, Zihan and Zhao, Shuang},
  journal = {ACM Transactions on Graphics / SIGGRAPH},
  volume = {40},
  number = {4},
  pages = {1--15},
  year = {2021},
  publisher = {ACM New York, NY, USA},
}