Zhimin Fan

(pronounced as Chih-Min Fan; 范之闽 in Chinese)

I'm a third-year master's student at Nanjing University, working with Prof. Jie Guo. I also work remotely with Prof. Ling-Qi Yan on various research projects. Prior to that, I received my bachelor's degree in Computer Science & Technology from Southeast University in 2023.

The goal of my research is to generate realistic images. My work centers on constraints in rendering, which define physically and computationally plausible solutions, ranging from physical constraints in specular light transport to computational constraints in Monte Carlo estimation. I would further explore extending these formulations toward data-driven and generative image synthesis, with an emphasis on controllability and physical consistency.

I will graduate in June 2026 and am actively seeking a Ph.D. position for Fall 2026.

CV (PDF) | Email | Github | Youtube

Zhimin Fan
A summary talk of my work on light transport with specular constraints is available: PDF (2.3MB, no animation), PPTX (95MB, recommend).

Publications

DSCombiner: Double Shrinkage for Combining Biased and Unbiased Monte Carlo Renderings
DSCombiner: Double Shrinkage for Combining Biased and Unbiased Monte Carlo Renderings
Chenxi Zhou, Keheng Xu, Mufan Guo, Xianhao Yu, Zhimin Fan, Guihuan Feng, Yanwen Guo, Jie Guo
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2025)
Paper

A two-step shrinkage estimator that flexibly combines biased, unbiased Monte Carlo renderings, and a denoised radiance prior under a hierarchical Bayesian framework.

Bernstein Bounds for Caustics
Bernstein Bounds for Caustics
Zhimin Fan, Chen Wang, Yiming Wang, Boxuan Li, Yuxuan Guo, Ling-Qi Yan, Yanwen Guo, Jie Guo
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2025)
Paper Supplementary Video Code Slides Presentation Fast-Forward

Deriving vertex position and irradiance bounds for each triangle tuple based on specular polynomials and Bernstein bounds for rational functions, reducing the search domain for specular light transport.

Multiple Importance Reweighting for Path Guiding
Multiple Importance Reweighting for Path Guiding
Zhimin Fan, Yiming Wang, Chenxi Zhou, Ling-Qi Yan, Yanwen Guo, Jie Guo
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2025)
Paper Supplementary Code Slides Presentation Fast-Forward

Combining the estimates generated in each guiding iteration by leveraging the importance distributions from multiple guiding iterations.

Specular Polynomials
Specular Polynomials
Zhimin Fan, Jie Guo, Yiming Wang, Tianyu Xiao, Hao Zhang, Chenxi Zhou, Zhenyu Chen, Pengpei Hong, Yanwen Guo, Ling-Qi Yan
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2024)
Paper Supplementary Slides Code

A polynomial formulation of specular constraints (multivariate & bivariate), converted into univariate polynomials using resultants, then efficiently solved.

Conditional Mixture Path Guiding
Conditional Mixture Path Guiding for Differentiable Rendering
Zhimin Fan, Pengcheng Shi, Mufan Guo, Ruoyu Fu, Yanwen Guo, Jie Guo
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2024)
Paper Slides Code

Importance sampling light path derivatives using a deterministic mixture of primal and differential distributions, with the optimal mixture weight conditioned on the BSDF of each vertex in the path prefix.

Manifold Path Guiding
Manifold Path Guiding for Importance Sampling Specular Chains
Zhimin Fan*, Pengpei Hong*, Jie Guo, Changqing Zou, Yanwen Guo, and Ling-Qi Yan
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2023)
Paper Supplementary Slides Code

Importance sampling specular chains with seed placement using continuous probability distributions reconstructed from historical samples.