Kernel Reformulation With Deep Constrained Least Squares for Blind Image Super-Resolution
IEEE Transactions on Circuits and Systems for Video Technology · 2025-08 · 35 (8) · 7380-7394
DOI: 10.1109/tcsvt.2025.3545606 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-08. Verfasst von Ziwei Luo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province.
Abstract (Originalsprache)
This work proposes to learn blind image super-resolution (SR) using deep constrained least squares deconvolution with low-resolution (LR) space kernels. Our method recovers the high-resolution (HR) image with a kernel estimation step and a kernel-based image restoration process. Specifically, we first reformulate the classical degradation model to transfer the deblurring kernel estimation into the LR space. We show that the LR space kernel has a closed-form solution given a pair of LR-HR images, which can be learned without ground truth kernels. Next, we introduce a dynamic deep linear filter module, which can generate deblurring kernel weights adaptively. Subsequently, the estimated kernel is integrated with a deep constrained least square filtering module to produce clean features. For reconstruction, we adopt a dual-path structured SR network that inputs both the deblurred feature and the original feature to suppress deconvolution artifacts. Finally, we learn discriminative features for deblurring and then restore the HR image in a single branch, producing a lighter weight network that can achieve comparable performance while only using 56% parameters and 60% inference time. Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves better accuracy and visual improvements against state-of-the-art approaches.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Sichuan Province
Zitieren
APA
Luo, Z., Huang, H., Yu, L., Li, Y., Zeng, B., & Liu, S. (2025). Kernel Reformulation With Deep Constrained Least Squares for Blind Image Super-Resolution. IEEE Transactions on Circuits and Systems for Video Technology, 35(8), 7380-7394. https://doi.org/10.1109/tcsvt.2025.3545606
Vancouver
Luo Z, Huang H, Yu L, Li Y, Zeng B, Liu S. Kernel Reformulation With Deep Constrained Least Squares for Blind Image Super-Resolution. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(8):7380-7394. doi:10.1109/tcsvt.2025.3545606
BibTeX
@article{Luo2025,
author = {Luo, Ziwei and Huang, Haibin and Yu, Lei and Li, Youwei and Zeng, Bing and Liu, Shuaicheng},
title = {Kernel Reformulation With Deep Constrained Least Squares for Blind Image Super-Resolution},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {8},
pages = {7380--7394},
doi = {10.1109/tcsvt.2025.3545606}
}
EUVIMED