Spatially-Aware Loss Functions for GAN-Driven Super-Resolution
IEEE Access · 2025 · 13 · 108561-108572
DOI: 10.1109/access.2025.3579004 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Xijun Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sony Research Program.
Abstract (Originalsprache)
Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, such as unexpected artifacts and noises. To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process. We extract spatial information from the input data and incorporate it into the training loss, making the corresponding loss a spatially adaptive (SA) one. After that, we utilize it to guide the training process. We will show that the proposed approach is independent of the methods used to extract the spatial information and independent of the SR tasks and models. This method consistently guides the training process towards generating visually pleasing SR images and video frames, substantially mitigating artifacts and noise, ultimately leading to enhanced perceptual quality.
Förderung
- Sony Research Program
Zitieren
APA
Wang, X., López-Tapia, S., Wu, X., Molina, R., & Katsaggelos, A. K. (2025). Spatially-Aware Loss Functions for GAN-Driven Super-Resolution. IEEE Access, 13, 108561-108572. https://doi.org/10.1109/access.2025.3579004
Vancouver
Wang X, López-Tapia S, Wu X, Molina R, Katsaggelos AK. Spatially-Aware Loss Functions for GAN-Driven Super-Resolution. IEEE Access. 2025;13:108561-108572. doi:10.1109/access.2025.3579004
BibTeX
@article{Wang2025,
author = {Wang, Xijun and López-Tapia, Santiago and Wu, Xinyi and Molina, Rafael and Katsaggelos, Aggelos K.},
title = {Spatially-Aware Loss Functions for GAN-Driven Super-Resolution},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {108561--108572},
doi = {10.1109/access.2025.3579004}
}
EUVIMED