Skip to Main content Skip to Navigation

Factorisation du rendu de Monte-Carlo fondée sur les échantillons et le débruitage bayésien

Abstract : 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 input data that we can get by gathering per-pixel sample statistics. In a second step, to factorize computations of interactive Monte Carlo rendering, we propose a new algorithm based on path tracing, called Dynamic Bayesian Caching. A clustering of pixels enables a smart grouping of many samples. Hence we can compute meaningful statistics on them. These statistics are compared with the ones that are stored in a cache to decide whether the former should replace or be merged with the latter. Finally, a Bayesian denoising, inspired from the works of the first part, is applied to enhance image quality.
Complete list of metadata

Cited literature [159 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Friday, April 26, 2019 - 4:56:16 PM
Last modification on : Saturday, June 25, 2022 - 9:12:36 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02112350, version 2


Malik Boughida. Factorisation du rendu de Monte-Carlo fondée sur les échantillons et le débruitage bayésien. Traitement des images [eess.IV]. Télécom ParisTech, 2017. Français. ⟨NNT : 2017ENST0013⟩. ⟨tel-02112350v2⟩



Record views


Files downloads