Monte Carlo ray tracing is known to be a particularly well-suited class of algorithms for photorealistic rendering. However, its fundamentally random nature breeds noise in the generated images. In this thesis, we develop new algorithms based on Monte Carlo samples and Bayesian inference in order to factorize rendering computations, by sharing information across pixels or by caching previous results. In the context of offline rendering, we build upon a recent denoising technique from the image processing community, called Non-local Bayes, to develop a new patch-based collaborative denoising algorithm, named Bayesian Collaborative Denoising. It is designed to be adapted to the specificities of Monte Carlo noise, and uses the additionnal inpu...
With the ongoing shift in the computer graphics industry toward Monte Carlo rendering, there is a ne...
Sampling is a key step in rendering pipeline. It allows the integration of light arriving to a point...
Rendering photo-realistic images of a virtual scene requires the simulation of how light interacts w...
Monte Carlo ray tracing is known to be a particularly well-suited class of algorithms for photoreali...
Le rendu de Monte-Carlo par lancer de rayons est connu depuis longtemps pour être une classe d’algor...
Denoising has proven to be useful to efficiently generate high-quality Monte Carlo renderings. Tradi...
Monte Carlo (MC) rendering systems can produce spectacular images but are plagued with noise at low ...
International audienceRecent work has shown that distributing Monte Carlo errors as a blue noise in ...
Monte Carlo rendering systems can produce important visual effects such as depth of field, motion bl...
Image filtering is often applied as a post-process to Monte Carlo generated pictures, in order to re...
Image filtering is often applied as a post-process to Monte Carlo generated pictures, in order to re...
Producing photorealistic images from a scene model requires computing a complex multidimensional int...
Abstract: Monte-Carlo methods of ray tracing allow generating physically correct images of...
Monte Carlo (MC) rendering systems can produce spectacular images but are plagued with noise at low ...
A novel post-processing approach for removing Monte Carlo noises in synthetic images is presented in...
With the ongoing shift in the computer graphics industry toward Monte Carlo rendering, there is a ne...
Sampling is a key step in rendering pipeline. It allows the integration of light arriving to a point...
Rendering photo-realistic images of a virtual scene requires the simulation of how light interacts w...
Monte Carlo ray tracing is known to be a particularly well-suited class of algorithms for photoreali...
Le rendu de Monte-Carlo par lancer de rayons est connu depuis longtemps pour être une classe d’algor...
Denoising has proven to be useful to efficiently generate high-quality Monte Carlo renderings. Tradi...
Monte Carlo (MC) rendering systems can produce spectacular images but are plagued with noise at low ...
International audienceRecent work has shown that distributing Monte Carlo errors as a blue noise in ...
Monte Carlo rendering systems can produce important visual effects such as depth of field, motion bl...
Image filtering is often applied as a post-process to Monte Carlo generated pictures, in order to re...
Image filtering is often applied as a post-process to Monte Carlo generated pictures, in order to re...
Producing photorealistic images from a scene model requires computing a complex multidimensional int...
Abstract: Monte-Carlo methods of ray tracing allow generating physically correct images of...
Monte Carlo (MC) rendering systems can produce spectacular images but are plagued with noise at low ...
A novel post-processing approach for removing Monte Carlo noises in synthetic images is presented in...
With the ongoing shift in the computer graphics industry toward Monte Carlo rendering, there is a ne...
Sampling is a key step in rendering pipeline. It allows the integration of light arriving to a point...
Rendering photo-realistic images of a virtual scene requires the simulation of how light interacts w...