Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

From Attention to Frequency: Integration of Vision Transformer and FFT-ReLU for Enhanced Image Deblurring

About

Image deblurring is vital in computer vision, aiming to recover sharp images from blurry ones caused by motion or camera shake. While deep learning approaches such as CNNs and Vision Transformers (ViTs) have advanced this field, they often struggle with complex or high-resolution blur and computational demands. We propose a new dual-domain architecture that unifies Vision Transformers with a frequency-domain FFT-ReLU module, explicitly bridging spatial attention modeling and frequency sparsity. In this structure, the ViT backbone captures local and global dependencies, while the FFT-ReLU component enforces frequency-domain sparsity to suppress blur-related artifacts and preserve fine details. Extensive experiments on benchmark datasets demonstrate that this architecture achieves superior PSNR, SSIM, and perceptual quality compared to state-of-the-art models. Both quantitative metrics, qualitative comparisons, and human preference evaluations confirm its effectiveness, establishing a practical and generalizable paradigm for real-world image restoration.

Syed Mumtahin Mahmud, Mahdi Mohd Hossain Noki, Prothito Shovon Majumder, Abdul Mohaimen Al Radi, Md. Haider Ali, Md. Mosaddek Khan• 2025

Related benchmarks

TaskDatasetResultRank
Image DeblurringGoPro (test)
PSNR32.92
672
Image DeblurringRealBlur-J (test)
PSNR28.99
259
Image DeblurringHIDE (test)
PSNR31.22
242
Image DeblurringRealBlur-R (test)--
17
Showing 4 of 4 rows

Other info

Follow for update