Corentin Salaün after defending his thesis. Photo: MPI-INF/Bertram Somieski
On 9 December 2025, Corentin Salaün successfully defended his PhD thesis with the title "Toward Improving Monte Carlo Estimator for Rendering and Machine Learning". He joined MPI for Informatics and Saarland University as a doctoral candidate in October 2020. The thesis was supervised by Prof. Dr. Hans-Peter Seidel, Scientific Director of the Computer Graphics department, and Gurprit Singh, head of the Sampling and Rendering group. The doctoral degree is awarded by Saarland University.
Abstract of the thesis:
Monte Carlo integration is a fundamental computational tool for estimating high-dimensional integrals that cannot be solved analytically. Its ability to handle complex domains and irregular functions makes it indispensable in computer graphics. One classical application is physically-based rendering that uses Monte Carlo integration to simulate the transport of light with photorealistic accuracy. Similar challenges arise in machine learning, where stochastic gradient estimation underpins the training of modern models and requires high-dimensional gradient estimation. In both domains, the accuracy and efficiency of Monte Carlo methods directly determine the quality of the final results.
This thesis introduces a set of new methods variance reduction techniques in both rendering and machine learning. It proposes adaptive control variates that automatically learn a control function from data, removing the need for hand-crafted designs while guaranteeing provable variance reduction. A scalable multi-class sampling framework is developed to generate a single set of samples that simultaneously satisfies multiple, potentially conflicting target distributions, and this framework is further extended to optimize perceptual image quality by incorporating models of human visual sensitivity. Finally, it presents efficient adaptive importance-sampling algorithms for stochastic gradient estimation, including a multi-distribution extension that combines several proposals with optimal weights to accelerate training. Together, these contributions advance the theoretical foundations of Monte Carlo integration and deliver practical algorithms that reduce error, improve efficiency, and enable new applications in photorealistic rendering and machine learning.