Efficient Image Enhancement With a Diffusion-Based Frequency Prior
IEEE Transactions on Circuits and Systems for Video Technology · 2025-09 · 35 (9) · 8452-8465
DOI: 10.1109/tcsvt.2025.3549351 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-09. Verfasst von Qingsen Yan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 77-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: NSFC of China, Natural Science Basic Research Program of Shaanxi, Fundamental Research Funds for Central Universities, and Guangdong Basic and Applied Basic Research Foundation.
Abstract (Originalsprache)
Due to the lack of appropriate priors, generating the content of dark regions remains a challenge in low-light image enhancement tasks. Currently, diffusion models employ robust image generation capabilities for enhancing low-light images. However, diffusion models require multiple iterations at the image feature level to generate details and content, which limits the speed. Moreover, the diffusion-based methods tend to generate unexpected artifacts in the degraded regions. To address these issues, we propose a Frequency Priors-guided Image Enhancement (FPIE) network, including a frequency prior generation network and an image restoration network. FPIE significantly accelerates inference by learning abstract prior with frequency domain constraints. Concretely, to learn compacted priors at the frequency domain, we introduce a joint training approach for the prior generation and restoration models to constrain the distribution of priors. Furthermore, to better utilize frequency-domain features for enhancing the network’s generation capabilities, a wavelet-based transformer block is introduced to produce intricate details and avoid the artifacts of the output. Extensive experimental results on the commonly used benchmarks demonstrate that our approach achieves state-of-the-art performances and well generalization to real-world images.
Förderung
- NSFC of China
- Natural Science Basic Research Program of Shaanxi
- Fundamental Research Funds for Central Universities, and Guangdong Basic and Applied Basic Research Foundation
Zitieren
APA
Yan, Q., Hu, T., Wu, P., Dai, D., Gu, S., Dong, W., & Zhang, Y. (2025). Efficient Image Enhancement With a Diffusion-Based Frequency Prior. IEEE Transactions on Circuits and Systems for Video Technology, 35(9), 8452-8465. https://doi.org/10.1109/tcsvt.2025.3549351
Vancouver
Yan Q, Hu T, Wu P, Dai D, Gu S, Dong W, et al. Efficient Image Enhancement With a Diffusion-Based Frequency Prior. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(9):8452-8465. doi:10.1109/tcsvt.2025.3549351
BibTeX
@article{Yan2025,
author = {Yan, Qingsen and Hu, Tao and Wu, Peng and Dai, Duwei and Gu, Shuhang and Dong, Wei and Zhang, Yanning},
title = {Efficient Image Enhancement With a Diffusion-Based Frequency Prior},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {9},
pages = {8452--8465},
doi = {10.1109/tcsvt.2025.3549351}
}
EUVIMED