Collaborative Blind Image Deblurring

TL;DR

This paper introduces a collaborative neural network approach for blind image deblurring that processes stacks of similar patches jointly, leading to improved accuracy in removing various types of blur.

Contribution

It proposes a novel neural architecture with a pooling layer for joint processing of image patches, enhancing deblurring performance over traditional separate patch handling.

Findings

Significant quantitative improvements on synthetic and real-world benchmarks.

Effective in sharpening images, removing camera shake, and correcting optical aberrations.

Outperforms existing methods in both accuracy and visual quality.

Abstract

Blurry images usually exhibit similar blur at various locations across the image domain, a property barely captured in nowadays blind deblurring neural networks. We show that when extracting patches of similar underlying blur is possible, jointly processing the stack of patches yields superior accuracy than handling them separately. Our collaborative scheme is implemented in a neural architecture with a pooling layer on the stack dimension. We present three practical patch extraction strategies for image sharpening, camera shake removal and optical aberration correction, and validate the proposed approach on both synthetic and real-world benchmarks. For each blur instance, the proposed collaborative strategy yields significant quantitative and qualitative improvements.