Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5665-5672
DOI: 10.1609/aaai.v40i7.37486 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hyeonjae Kim und 3 weiteren Autor:innen.
Abstract (Originalsprache)
While deep learning-based super-resolution (SR) methods have shown impressive outcomes with synthetic degradation scenarios such as bicubic downsampling, they frequently struggle to perform well on real-world images that feature complex, nonlinear degradations like noise, blur, and compression artifacts. Recent efforts to address this issue have involved the painstaking compilation of real low-resolution (LR) and high-resolution (HR) image pairs, usually limited to several specific downscaling factors. To address these challenges, our work introduces a novel framework capable of synthesizing authentic LR images from a single HR image by leveraging the latent degradation space with flow matching. Our approach generates LR images with realistic artifacts at unseen degradation levels, which facilitates the creation of large-scale, real-world SR training datasets. Comprehensive quantitative and qualitative assessments verify that our synthetic LR images accurately replicate real-world degradations. Furthermore, both traditional and arbitrary-scale SR models trained using our datasets consistently yield much better HR outcomes.
Zitieren
APA
Kim, H., Kim, D., Jin, E., & Kim, T. H. (2026). Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5665-5672. https://doi.org/10.1609/aaai.v40i7.37486
Vancouver
Kim H, Kim D, Jin E, Kim TH. Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5665-5672. doi:10.1609/aaai.v40i7.37486
BibTeX
@article{Kim2026,
author = {Kim, Hyeonjae and Kim, Dongjin and Jin, Eugene and Kim, Tae Hyun},
title = {Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {7},
pages = {5665--5672},
doi = {10.1609/aaai.v40i7.37486}
}
EUVIMED