Article Dans Une Revue ACM Transactions on Multimedia Computing, Communications and Applications Année : 2025

Style-FG: A Style-based Framework for Film Grain Analysis and Synthesis

Résumé

Film grain which used to be a by-product of the chemical processing in the analog film stock is a desirable feature in the era of digital cameras. Besides participating to the artistic intent during content creation, film grain has also interesting properties in the video compression chain such as its ability to mask compression artifacts. In this article, we use a deep learning-based framework for film grain analysis, generation, and synthesis. Our framework Style-FG consists of three modules: a style encoder performing film grain style analysis, a mapping network responsible for film grain style generation, and a synthesis network that generates and blends a specific grain style to a given content in a content-adaptive manner. All modules are trained jointly, thanks to dedicated loss functions, on a new large and diverse dataset of pairs of grain-free and grainy images that we made publicly available to the community. 1 Quantitative and qualitative evaluations show that fidelity to the reference grain, diversity of grain styles as well as a perceptually pleasant grain synthesis are achieved, demonstrating that each module outperforms the state-of-the-art in the task it was designed for. To contribute further to the sustainability necessary effort of the digital information and communication field, a light-weight version of Style-FG is also proposed, which demonstrates similar quantitative and qualitative performances, while reducing the number of network parameters by a factor of 92%.

Fichier principal
Vignette du fichier
Ameur et al. - 2025 - Style-FG a style-based framework for film grain analysis and synthesis.pdf (32.23 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05251455 , version 1 (12-09-2025)

Licence

Identifiants

Citer

Zoubida Ameur, Claire-Hélène Demarty, Olivier Le Meur, Daniel Ménard. Style-FG: A Style-based Framework for Film Grain Analysis and Synthesis. ACM Transactions on Multimedia Computing, Communications and Applications, 2025, 21 (9), pp.1-24. ⟨10.1145/3712592⟩. ⟨hal-05251455⟩
87 Consultations
130 Téléchargements

Altmetric

Partager

  • More