Learning Collaborative Generation Correction Modules for Blind Image Deblurring and Beyond

TL;DR

This paper introduces a collaborative learning framework with Generator and Corrector modules for blind image deblurring, ensuring convergence to optimal solutions and outperforming existing methods on various datasets.

Contribution

It proposes a novel collaborative modules approach with theoretical convergence guarantees for blind image deblurring and extends to related tasks.

Findings

Outperforms state-of-the-art methods on synthetic datasets.

Achieves superior results on real-world images.

Demonstrates convergence to optimal solutions.

Abstract

Blind image deblurring plays a very important role in many vision and multimedia applications. Most existing works tend to introduce complex priors to estimate the sharp image structures for blur kernel estimation. However, it has been verified that directly optimizing these models is challenging and easy to fall into degenerate solutions. Although several experience-based heuristic inference strategies, including trained networks and designed iterations, have been developed, it is still hard to obtain theoretically guaranteed accurate solutions. In this work, a collaborative learning framework is established to address the above issues. Specifically, we first design two modules, named Generator and Corrector, to extract the intrinsic image structures from the data-driven and knowledge-based perspectives, respectively. By introducing a collaborative methodology to cascade these modules, we can strictly prove the convergence of our image propagations to a deblurring-related optimal solution. As a nontrivial byproduct, we also apply the proposed method to address other related tasks, such as image interpolation and edge-preserved smoothing. Plenty of experiments demonstrate that our method can outperform the state-of-the-art approaches on both synthetic and real datasets.