Gurprit Singh

Welcome!

I am leading the sampling and rendering group in the computer graphics department at the Max Planck Institute for informatics in Saarbrücken, Germany. Before that, I spent two wonderful years at Dartmouth College working with Wojciech Jarosz followed by another two-year postdoc working with Karol Myszkowski. I obtained my PhD from Université Lyon 1 in France, under the supervision of Victor Ostromoukhov.

How To Do Research (Bill Freeman's notes)
Writing tips (Wojciech Jarosz)

Pipeline teaser image
Best way to reach me.

X-Twitter: @sinbagga

Research

My research revolves around sampling which is the basic building block in many domains including computer graphics, computer vision, machine learning and generative AI. I strive to understand how different sample correlations affect specific applications and I enjoy developing models to characterize these correlations using various mathematical tools. For example, sample distributions directly affect the error during Monte Carlo and Quasi-Monte Carlo (MCQMC) based numerical estimations of global illumination integrals. Similar numerical approximations are extremely important in quantitative analysis in financial math. On the vision side, the data obtained from scanners in the form of noisy point clouds needs constant improvement for fast and better detection, segmentation and reconstruction of underlying objects/material properties. Similar problems are also encountered in computational geometry for remeshing. In all, I am interested in various aspects of sample correlations/distributions. If you have a specific question or if you wonder why some distributions in nature are the way they are, feel free to send me an email.

Open positions, PhD students, teaching

Academic service

SIGGRAPH 2024: Technical program committee member for SIGGRAPH North America
EG 2024: International program committee member for Eurographics
CVM 2024: International program committee member for Computational visual media
EGSR 2022-Present: Technical program committee member for Eurographics symposium on rendering
EG 2023: Co-chairing Posters and the Diversity & Inclusion Program
SIGGRAPH Asia 2022: International program committee member for SIGGRAPH Asia.
EGSR 2021: Conference co-chair with Pascal Grittmann and Philipp Slusallek (Saarland University).
EG 2020-21: International program committee member for Eurographics Short papers.
PG 2019-21: International program committee member for Pacific Graphics.
Reviewer: SIGGRAPH, TOG, Eurographics (EG), EGSR, Pacific Graphics, JCST, HELIYON (Elsevier).

Publications

2024

Blue noise for diffusion models

SIGGRAPH North America 2024
Xingchang Huang, Corentin Salaun, Cristina Vasconcelos, Christian Theobalt, Cengiz Oztireli, Gurprit Singh
Q:How can we enhance the generated samples simply from noise manipulation?
webpage arXiv

2023

Efficient gradient estimation via adaptive sampling and importance sampling

Corentin Salaun, Xingchang Huang, Iliyan Georgiev, Niloy Mitra, Gurprit Singh
Q: Is there an efficient way to assign importance weight to mini-batch samples in gradient estimation?
webpage arXiv

Joint sampling and optimisation for inverse rendering

SIGGRAPH Asia 2023
Martin Balint, Karol Myszkowski, Hans-Peter Seidel, Gurprit Singh
Q: How to reduce variance in gradient estimation during inverse rendering?
webpage arXiv

Perceptual error optimization for Monte Carlo animation rendering

SIGGRAPH Asia 2023 (conference track)
Misa Korac*, Corentin Salaun*, Iliyan Georgiev, Pascal Grittmann, Philipp Slusallek, Karol Myszkowski, Gurprit Singh
Q: How to design perceptually motivated spatio-temporal masks for Monte carlo animation rendering?
webpage arXiv (*joint first authors)

Patternshop: Editing point patterns with image manipulations

SIGGRAPH North America 2023
Xingchang Huang, Tobias Ritschel, Hans-Peter Seidel, Pooran Memari, Gurprit Singh
Q: How can we design a 2D color-space that allows editing point patterns with Photoshop?
webpage arXiv

2022

Informatik spectrum: Scalable multi-class sampling via filtered sliced optimal transport

Cover Image for Informatik Spectrum, October 2022
Corentin Salaun, Iliyan Georgiev, Hans-Peter Seidel, Gurprit Singh
Journal

Scalable multi-class sampling via filtered sliced optimal transport

SIGGRAPH Asia 2022 / ACM Transactions on Graphics, Volume 41 issue 6, December 2022
Corentin Salaun, Iliyan Georgiev, Hans-Peter Seidel, Gurprit Singh
Q: How can we build a unified framework for stippling, object placement and perceptually pleasing rendering?
webpage arXiv

Point-pattern synthesis using Gabor and random filters

EGSR 2022 / Computer Graphics Forum, Volume 41 issue 6, July 2022
Xingchang Huang, Pooran Memari, Hans-Peter Seidel, Gurprit Singh
Q: How can we perform point pattern (texture) synthesis without training a network?
webpage

Regression-based Monte Carlo integration

SIGGRAPH North America 2022 / ACM Transactions on Graphics, Volume 41 issue 4, July 2022
Corentin Salaun, Adrien Gruson, Binh-Son Hua, Toshiya Hachisuka, Gurprit Singh
Q: What happens if we use a polynomial function to average Monte Carlo estimates?
webpage arXiv

Perceptual error optimization for Monte Carlo rendering

ACM Transactions on Graphics, Volume 41 issue 3, June 2022 (presented at SIGGRAPH North America 2022)
Vassillen Chizhov, Iliyan Georgiev, Karol Myszkowski, Gurprit Singh
Q: How can we use a perception-based (human visual system) model to control the error distribution in rendering?
webpage arXiv

2021

Informatik Spectrum: Neural Light Field 3D Printing

Cover Image for Informatik Spectrum, October 2021
Quan Zheng, Vahid Babaei, Gordon Wetzstein, Hans-Peter Seidel, Matthias Zwicker, Gurprit Singh
summary
Magazine Journal

Neural Relightable Participating Media Rendering

NeurIPS 2021
Quan Zheng, Gurprit Singh, Hans-Peter Seidel
summary
arXiv

Blue Noise Plots

Eurographics 2021 / Computer Graphics Forum, Volume 40 issue 2, May 2021
Christian van Onzenoodt, Gurprit Singh, Timo Ropinski, Tobias Ritschel
summary
arXiv source code

2020

Neural Light Field 3D Printing

SIGGRAPH ASIA 2020 / ACM Transactions on Graphics, Volume 39 issue 6, December 2020
Quan Zheng, Vahid Babaei, Gordon Wetzstein, Hans-Peter Seidel, Matthias Zwicker, Gurprit Singh
summary
webpage

LadyBird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry

ECCV (Oral), August 2020
Yifan Xu*, Tianqi Fan*, Yi Yuan, Gurprit Singh (*contributed equally)
summary
webpage

Real-time Monte Carlo Denoising with the Neural Bilateral Grid

Eurographics Symposium on Rendering (EGSR), June 2020
Xiaoxu Meng, Quan Zheng, Amitabh Varshney, Gurprit Singh, Matthias Zwicker
summary
webpage

2019

Deep Point Correlation Design

SIGGRAPH ASIA 2019 / ACM Transactions on Graphics, Volume 38 issue 6, October 2019
Thomas Leimkühler, Gurprit Singh, Karol Myszkowski, Hans-Peter Seidel, Tobias Ritschel
summary
webpage

Analysis of Sample Correlations for Monte Carlo Rendering

Computer Graphics Forum (Proceedings of Eurographics - State of the art reports) 2019
Gurprit Singh, Cengiz Öztireli, Abdalla G.M. Ahmed, David Coeurjolly, Kartic Subr, Oliver Deussen, Victor Ostromoukhov, Ravi Ramamoorthi, Wojciech Jarosz
summary
webpage

Fourier Analysis of Correlated Monte Carlo Importance Sampling

Computer Graphics Forum, 38(1), 2019
Gurprit Singh, Kartic Subr, David Coeurjolly, Victor Ostromoukhov, Wojciech Jarosz
summary
webpage

A Perception-driven Hybrid Decomposition for Multi-layer Accommodative Displays

IEEE VR 2019
Hyeonseung Yu, Mojtaba Bemana, Marek Wernikowski, Michał Chwesiuk, Okan Tarhan Tursun, Gurprit Singh, Karol Myszkowski, Radosław Mantiuk, Hans-Peter Seidel, Piotr Didyk
summary
webpage

2018

Spectral Measures of Distortion for Change Detection in Dynamic Graphs

Complex Networks 2018 (Oral)
Luca Castelli Aleardi, Semih Salihoglu, Gurprit Singh, Maks Ovsjanikov
summary
webpage

Sampling Analysis using Correlations for Monte Carlo Rendering

SIGGRAPH Asia Courses 2018
Cengiz Öztireli, Gurprit Singh
summary
webpage

End-to-end Sampling Patterns

Thomas Leimkühler, Gurprit Singh, Karol Myszkowski, Hans-Peter Seidel, Tobias Ritschel
summary
Technical Report

2017

Convergence Analysis for Anisotropic Monte Carlo Sampling Spectra

SIGGRAPH 2017 / ACM Transactions on Graphics, 36 (4), July 2017
Gurprit Singh, Wojciech Jarosz
summary
webpage

Variance and Convergence Analysis of Monte Carlo Line and Segment Samples

Computer Graphics Forum (Proceedings of EGSR), 36 (4), June 2017
Gurprit Singh, Bailey Miller, Wojciech Jarosz
summary
webpage source code (AO example)

2016

Monte Carlo Convergence Analysis for Anisotropic Sampling Power Spectra

Gurprit Singh, Wojciech Jarosz
summary
Technical Report

Fourier Analysis of Numerical Integration in Monte Carlo Rendering: Theory and Practice

SIGGRAPH Courses 2016
Kartic Subr, Gurprit Singh, Wojciech Jarosz
summary
webpage acm.org source code

2015

Variance and Sampling Analysis for Monte Carlo Integration in the Spherical Domain

Ph.D. Dissertation, Université Lyon 1, France, September 2015.
Gurprit Singh
summary
HAL

Variance Analysis for Monte Carlo Integration

SIGGRAPH 2015 / ACM Transactions on Graphics, 34 (4), 2015
*Adrien Pilleboue, *Gurprit Singh, David Coeurjolly, Michael Kazhdan, Victor Ostromoukhov (*joint first authors)
summary
webpage acm.org source code

Variance Analysis for Monte Carlo Integration: A Representation-Theoretic Perspective

Michael Kazhdan, Gurprit Singh, Adrien Pilleboue, David Coeurjolly, Victor Ostromoukhov
summary
arXiv Report

2014

Fast Tile-Based Adaptive Sampling with User-Specified Fourier Spectra

SIGGRAPH 2014 / ACM Transactions on Graphics, 33 (4), 2014
Florent Wachtel, Adrien Pilleboue, David Coeurjolly, Katherine Breeden, Gurprit Singh, Gaël Cathelin, Fernando de Goes, Mathieu Desbrun, Victor Ostromoukhov
summary
webpage acm.org

Imprint / Data Protection