Multi-scale Frequency Enhancement Network for Blind Image Deblurring

TL;DR

This paper introduces MFENet, a novel multi-scale frequency enhancement network for blind image deblurring that effectively captures multi-scale features and high-frequency details, improving image clarity and downstream detection tasks.

Contribution

The paper proposes a multi-scale feature extraction module and a frequency enhancement module using wavelet transforms, addressing non-uniform blur and texture reconstruction challenges.

Findings

Outperforms existing methods on GoPro and HIDE datasets.

Improves object detection accuracy after deblurring.

Achieves superior visual and quantitative deblurring results.

Abstract

Image deblurring is an essential image preprocessing technique, aiming to recover clear and detailed images form blurry ones. However, existing algorithms often fail to effectively integrate multi-scale feature extraction with frequency enhancement, limiting their ability to reconstruct fine textures. Additionally, non-uniform blur in images also restricts the effectiveness of image restoration. To address these issues, we propose a multi-scale frequency enhancement network (MFENet) for blind image deblurring. To capture the multi-scale spatial and channel information of blurred images, we introduce a multi-scale feature extraction module (MS-FE) based on depthwise separable convolutions, which provides rich target features for deblurring. We propose a frequency enhanced blur perception module (FEBP) that employs wavelet transforms to extract high-frequency details and utilizes multi-strip pooling to perceive non-uniform blur, combining multi-scale information with frequency enhancement to improve the restoration of image texture details. Experimental results on the GoPro and HIDE datasets demonstrate that the proposed method achieves superior deblurring performance in both visual quality and objective evaluation metrics. Furthermore, in downstream object detection tasks, the proposed blind image deblurring algorithm significantly improves detection accuracy, further validating its effectiveness androbustness in the field of image deblurring.