Jérôme Buisine

Jérôme Buisine
Université du Littoral Côte d'Opale (ULCO) | ULCO · Laboratoire d’Informatique, Signal et Image de la Côte d’opale - LISIC

PhD in Machine Learning and Computer Graphics

About

5
Publications
569
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
5
Citations
Introduction
My research work is mainly focused on Noise perception of physically based rendering of synthesis images (Monte-Carlo method) using machine learning. I also work on underlying topics such as statistics extractions combined with deep learning methods for image denoising and the use of Surrogate models inside operations research process for features selection.

Publications

Publications (5)
Conference Paper
Full-text available
Estimating the rendering equation using Monte Carlo methods produces photorealistic images by evaluating a large number of samples of the rendering equation per pixel. The final value for each pixel is then calculated as the average of the contribution of each sample. The mean is a good estimator, but not necessarily robust which explains the appea...
Article
Full-text available
The estimation of image quality and noise perception still remains an important issue in various image processing applications. It has also become a hot topic in the field of photo-realistic computer graphics where noise is inherent in the calculation process. Unlike natural-scene images, however, a reference image is not available for computer-gen...
Thesis
Full-text available
Les méthodes de simulation de l'éclairage, utilisées en synthèse d'images, permettent d'obtenir des vues dites photo-réalistes d'environnements virtuels 3D. Pour ce faire, elles utilisent des méthodes stochastiques, s'appuyant sur la théorie des grands nombres, qui explorent l'espace des chemins lumineux et se caractérisent par une convergence prog...

Network

Cited By