From last 10 years or so, I have spent most of my time developing mathematical models to understand the role of randomness. I am fascinated by noise. Currently, I am investigating how noise plays a pivotal role in generative AI models. Before that, I spent a decade understanding how noise impacts the convergence behaviour of various rendering systems (for physically based light transport).

Myself Gurpreet, I come from a small town Jalandhar in Punjab, India. I did my schooling from Kendriya Vidyalaya No. 2, Jalandhar. I got into IIT Delhi and from there my journey started.

At the core of my research, I develop Monte Carlo sampling strategies for high-dimensional numerical integration problems. I am equally interested in applying Monte Carlo, Quasi-Monte Carlo and MCMC sampling strategies in the area of generative modeling.

Recent Publications

2025

Jump restore light transport

Sascha Holl, Gurprit Singh, Hans-Peter Seidel

SIGGRAPH Asia 2025

project page / arXiv


Gaussian integral linear operators for precomputed graphics

Haolin Lu, Yash Belhe, Gurprit Singh, Tzu-Mao Li, Toshiya Hachisuka

SIGGRAPH Asia 2025

project page


Histogram Stratification for Spatio-Temporal Reservoir Sampling

Corentin Salaün, Martin Bálint, Laurent Belcour, Eric Heitz, Gurprit Singh and Karol Myszkowski

SIGGRAPH North America 2025

project page


Demystifying noise: Role of randomness in generative AI

Gurprit Singh, Xingchang Huang, Jente Vandersanden, Cengiz Öztireli, Niloy Mitra

SIGGRAPH North America Courses 2025 / Eurographics Tutorial 2025

project page


Edge-preserving noise for diffusion models

Jente Vandersanden, Sascha Holl, Xingchang Huang, Gurprit Singh

ICLR Workshop 2025

project page / arXiv


Online importance sampling for stochastic gradient optimization

Corentin Salaun, Xingchang Huang, Iliyan Georgiev, Niloy Mitra, Gurprit Singh

ICPRAM 2025 (Best Student Paper Award)

project page / arXiv


Multiple importance sampling for stochastic gradient estimation

Corentin Salaun, Xingchang Huang, Iliyan Georgiev, Niloy Mitra, Gurprit Singh

ICPRAM 2025

project page / arXiv


2024

MCMC: Bridging Rendering, Optimization and Generative AI

Gurprit Singh, Wenzel Jakob

SIGGRAPH Asia Courses 2024

project page / arXiv


Blue noise for diffusion models

Xingchang Huang, Corentin Salaun, Cristina Vasconcelos, Christian Theobalt, Cengiz Oztireli, Gurprit Singh

SIGGRAPH North America 2024

project page / arXiv