Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

non-blind deblurring

Non-blind deblurring is an image restoration process that recovers a sharp, clear image from a blurred input under the condition that the blur kernel or point spread function is already known. Unlike blind deblurring, which must estimate both the latent image and the unknown degradation process simultaneously, non-blind methods formulate restoration as an inverse problem with a predetermined blur operator. The degradation is typically modeled as a mathematical convolution between the sharp image and the blur kernel, accompanied by additive noise. Because direct mathematical inversion tends to amplify noise and generate visual artifacts such as ringing, non-blind deblurring techniques utilize regularization strategies, classical iterative deconvolution algorithms, or deep learning models to stabilize the reconstruction and synthesize visually coherent spatial details.

1 item

Dual-Domain Attention for Image Deblurring

Dual-Domain Attention for Image Deblurring

Yuning Cui, Yi Tao, Wenqi Ren, Alois Knoll

OrganizationsMassachusetts Institute of TechnologySun Yat-sen UniversityTechnical University of Munich

Why you should read this

Proposes a dual-domain attention network that pairs dynamic group convolution for localized spatial self-attention with a lightweight frequency-decoupling module, achieving state-of-the-art image deblurring quality with substantially faster inference speeds.

As a long-standing and challenging task, image deblurring aims to reconstruct the latent sharp image from its degraded counterpart. In this study, to bridge the gaps between degraded/sharp image pairs in the spatial and frequency domains simultaneously, we develop the dual-domain attention mechanism for image deblurring. Self-attention is widely used in vision tasks, however, due to the quadratic complexity, it is not applicable to image deblurring with high-resolution images. To alleviate this issue, we propose a novel spatial attention module by implementing self-attention in the style of dynamic group convolution for integrating information from the local region, enhancing the representation learning capability and reducing computational burden. Regarding frequency domain learning, many frequency-based deblurring approaches either treat the spectrum as a whole or decompose frequency components in a complicated manner. In this work, we devise a frequency attention module to compactly decouple the spectrum into distinct frequency parts and accentuate the informative part with extremely lightweight learnable parameters. Finally, we incorporate attention modules into a U-shaped network. Extensive comparisons with prior arts on the common benchmarks show that our model, named Dual-Domain Attention Network (DDANet), obtains comparable results with a significantly improved inference speed.

Added

2026-09-26