About me
I am currently a Maître de conférences (Associate Professor) at Université Claude Bernard Lyon-1, where I conduct research at the intersection of computer graphics, rendering, and perception.
My research focuses on real-time physically based rendering, with a particular interest in sampling, perceptual modeling, and efficient image reconstruction. I am especially interested in understanding how human visual perception can be integrated into rendering algorithms to improve the quality and efficiency of real-time graphics. My work also explores real-time denoising and reconstruction techniques for noisy Monte Carlo rendered images, with the goal of producing high-quality imagery under tight computational constraints.
My main research interests include:
- Real-time physically based rendering
- Monte Carlo sampling and variance reduction
- Applied perception for computer graphics
- Perceptual sampling and rendering
- Real-time denoising and image reconstruction
- Blue-noise error distributions and sampling correlations
- Multiple importance sampling
- Spatiotemporal sampling and reconstruction
Latest publications
| | Histogram Stratification for Spatio-Temporal Reservoir SamplingCorentin Salaün, Martin Bálint, Laurent Belcour, Eric Heitz, Gurprit Singh and Karol Myszkowski ACM Siggraph 2025 (Conference track) Recommended citation: Salaun, Corentin. (2025). "Histogram Stratification for Spatio-Temporal Reservoir Sampling" SIGGRAPH 2025 Conference Papers. |
| | Online Importance Sampling for Stochastic Gradient OptimizationCorentin Salaün, Xingchang Huang, Iliyan Georgiev, Niloy J. Mitra, Gurprit Singh ICPRAM 2025 (Full Paper) Best Student Paper Award Recommended citation: Salaun, Corentin. (2025). "Online Importance Sampling for Stochastic Gradient Optimization" ICPRAM 2025. |
| | Multiple Importance Sampling for Stochastic Gradient EstimationCorentin Salaün, Xingchang Huang, Iliyan Georgiev, Niloy J. Mitra, Gurprit Singh ICPRAM 2025 (Short Paper) Recommended citation: Salaun, Corentin. (2025). "Multiple Importance Sampling for Stochastic Gradient Estimation" ICPRAM 2025. |
