Towards Differential Handling of Various Blur Regions for Accurate Image Deblurring

TL;DR

This paper introduces DHNet, a novel image deblurring network that adaptively handles different blur regions by integrating nonlinear characteristics and degradation recognition, outperforming existing methods on various datasets.

Contribution

The paper proposes a differential handling network with a Volterra block and a degradation recognition expert module for adaptive image deblurring, addressing varying blur degrees more effectively.

Findings

DHNet surpasses state-of-the-art methods on synthetic datasets.

DHNet performs well on real-world blurred images.

The model adaptively allocates processing based on blur severity.

Abstract

Image deblurring aims to restore high-quality images by removing undesired degradation. Although existing methods have yielded promising results, they either overlook the varying degrees of degradation across different regions of the blurred image, or they approximate nonlinear function properties by stacking numerous nonlinear activation functions. In this paper, we propose a differential handling network (DHNet) to perform differential processing for different blur regions. Specifically, we design a Volterra block (VBlock) to integrate the nonlinear characteristics into the deblurring network, avoiding the previous operation of stacking the number of nonlinear activation functions to map complex input-output relationships. To enable the model to adaptively address varying degradation degrees in blurred regions, we devise the degradation degree recognition expert module (DDRE). This module initially incorporates prior knowledge from a well-trained model to estimate spatially variable blur information. Consequently, the router can map the learned degradation representation and allocate weights to experts according to both the degree of degradation and the size of the regions. Comprehensive experimental results show that DHNet effectively surpasses state-of-the-art (SOTA) methods on both synthetic and real-world datasets.