DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring

TL;DR

This paper introduces DWDN, a novel non-blind image deblurring method that combines classical Wiener deconvolution with deep learning in a feature space, achieving superior results with fewer artifacts.

Contribution

The paper proposes a deep Wiener deconvolution network that integrates classical deconvolution in feature space with multi-scale refinement, improving non-blind image deblurring performance.

Findings

Outperforms state-of-the-art methods in quantitative metrics.

Produces deblurred images with fewer artifacts.

Effective on real-world images with noise and artifacts.

Abstract

We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning. In contrast to existing methods that deblur the image directly in the standard image space, we propose to perform an explicit deconvolution process in a feature space by integrating a classical Wiener deconvolution framework with learned deep features. A multi-scale cascaded feature refinement module then predicts the deblurred image from the deconvolved deep features, progressively recovering detail and small-scale structures. The proposed model is trained in an end-to-end manner and evaluated on scenarios with simulated Gaussian noise, saturated pixels, or JPEG compression artifacts as well as real-world images. Moreover, we present detailed analyses of the benefit of the feature-based Wiener deconvolution and of the multi-scale cascaded feature refinement as well as the robustness of the proposed approach. Our extensive experimental results show that the proposed deep Wiener deconvolution network facilitates deblurred results with visibly fewer artifacts and quantitatively outperforms state-of-the-art non-blind image deblurring methods by a wide margin.