Rémi Synave

Dr. Rémi Synave

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 January 2021 in Entropy
Verified
Journal Article
Open access
PDF file
Jérôme BUISINEJérôme BUISINE
Jérôme BUISINE
Andre BigandAndre Bigand
Andre Bigand
RSRémi Synave
Rémi Synave
SDSamuel Delepoulle
Samuel Delepoulle
Christophe RenaudChristophe Renaud
Christophe Renaud
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-generated images. Thus, classic methods to assess noise quantity and stopping criterion during the rendering process are not usable. This is particularly important in the case of global illumination methods based on stochastic techniques: They provide photo-realistic images which are, however, corrupted by stochastic noise. This noise can be reduced by increasing the number of paths, as proved by Monte Carlo theory, but the problem of finding the right number of paths that are required in order to ensure that human observers cannot perceive any noise is still open. Until now, the features taking part in the human evaluation of image quality and the remaining perceived noise are not precisely known. Synthetic image generation tends to be very expensive and the produced datasets are high-dimensional datasets. In that case, finding a stopping criterion using a learning framework is a challenging task. In this paper, a new method for characterizing computational noise for computer generated images is presented. The noise is represented by the entropy of the singular value decomposition of each block composing an image. These Singular Value Decomposition (SVD)-entropy values are then used as input to a recurrent neural network architecture model in order to extract image noise and in predicting a visual convergence threshold of different parts of any image. Thus a new no-reference image quality assessment is proposed using the relation between SVD-Entropy and perceptual quality, based on a sequence of distorted images. Experiments show that the proposed method, compared with experimental psycho-visual scores, demonstrates a good consistency between these scores and stopping criterion measures that we obtain.

25 December 2023 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
JZJing ZHANG
Jing ZHANG
RSRémi Synave
Rémi Synave
SDSamuel Delepoulle
Samuel Delepoulle
Rémi CozotRémi Cozot
Rémi Cozot
The composition of an image is a critical element chosen by the author to construct an image that conveys a narrative and related emotions. Other key elements include framing, lighting, and colors. Assessing classical and simple composition rules in an image, such as the well-known “rule of thirds”, has proven effective in evaluating the aesthetic quality of an image. It is widely acknowledged that composition is emphasized by the presence of leading lines. While these leading lines may not be explicitly visible in the image, they connect key points within the image and can also serve as boundaries between different areas of the image. For instance, the boundary between the sky and the ground can be considered a leading line in the image. Making the image’s composition explicit through a set of leading lines is valuable when analyzing an image or assisting in photography. To the best of our knowledge, no computational method has been proposed to trace image leading lines. We conducted user studies to assess the agreement among image experts when requesting them to draw leading lines on images. According to these studies, which demonstrate that experts concur in identifying leading lines, this paper introduces a fully automatic computational method for recovering the leading lines that underlie the image’s composition. Our method consists of two steps: firstly, based on feature detection, potential weighted leading lines are established; secondly, these weighted leading lines are grouped to generate the leading lines of the image. We evaluate our method through both subjective and objective studies, and we propose an objective metric to compare two sets of leading lines.

2 February 2026 in AI and Ethics
Verified
Journal Article
Closed access
PDF file
FVFranck Vandewiele
Franck Vandewiele
RSRémi Synave
Rémi Synave
SDSamuel Delepoulle
Samuel Delepoulle
Rémi CozotRémi Cozot
Rémi Cozot

30 March 2026
Verified
Thesis
Closed access
RSRémi Synave
Rémi Synave
Le scanner laser est un périphérique permettant d'analyser un objet réel et d'extraire des informations de sa surface. Grâce à cet outil, il est possible d'obtenir la représentation numérique de tout ou partie de la surface frontière d'un objet réel. Les scanners laser sont livrés avec un logiciel permettant de faire l'acquisition des données brutes, le recalage des différentes parties acquises et la reconstruction de la surface. Cette suite d'opérations permet de construire le modèle numérique et est communément appelée pipeline 3D d'acquisition. Dans cette thèse, nous développons notre pipeline, que nous nommons A2RI, et y ajoutons une étape d'impression. Ce pipeline permet la reproduction d'un objet à partir de son acquisition au scanner laser. Nous veillons particulièrement à quantifier et maîtriser l'erreur commise dans chaque maillon de la chaîne grâce à des mesures euclidiennes et géodésiques sur l'objet réel et le modèle numérique.

28 September 2022 in J3eA
Verified
Journal Article
Open access
PDF file
RSRémi Synave
Rémi Synave
Lors de l’année scolaire 2017-2018, les étudiants de DUT Informatique de l’IUT du Littoral Côte d’Opale (IUTLCO) et les élèves du Lycée Professionnel Giraux Sannier de Saint-Martin-Boulogne ont travaillé à l’élaboration d’une borne d’arcade. Ce projet a nécessité la mise en commun des compétences des deux établissements ainsi que celles du FabLab Côte d’Opale. Il a aussi permis au département informatique de l’IUTLCO de se doter d’un nouvel outil de communication.

17 February 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
GLGuérin Louis
Guérin Louis
JZJing Zhang
Jing Zhang
RSRémi Synave
Rémi Synave
SDSamuel Delepoulle
Samuel Delepoulle
RCRémi Cozot
Rémi Cozot