SharpGAN: Receptive Field Block Net for Dynamic Scene Deblurring

TL;DR

SharpGAN introduces a novel deblurring network incorporating Receptive Field Block Net and feature loss, significantly enhancing real-time motion deblurring performance for smart ships navigating turbulent sea conditions.

Contribution

The paper proposes SharpGAN, a new GAN-based deblurring method with RFBNet and feature loss, improving both deblurring quality and efficiency for maritime applications.

Findings

Superior visual and quantitative deblurring results

Enhanced real-time performance with lightweight modules

Effective on large-scale sea image datasets

Abstract

When sailing at sea, the smart ship will inevitably produce swaying motion due to the action of wind, wave and current, which makes the image collected by the visual sensor appear motion blur. This will have an adverse effect on the object detection algorithm based on the vision sensor, thereby affect the navigation safety of the smart ship. In order to remove the motion blur in the images during the navigation of the smart ship, we propose SharpGAN, a new image deblurring method based on the generative adversarial network. First of all, the Receptive Field Block Net (RFBNet) is introduced to the deblurring network to strengthen the network's ability to extract the features of blurred image. Secondly, we propose a feature loss that combines different levels of image features to guide the network to perform higher-quality deblurring and improve the feature similarity between the restored images and the sharp image. Finally, we propose to use the lightweight RFB-s module to improve the real-time performance of deblurring network. Compared with the existing deblurring methods on large-scale real sea image datasets and large-scale deblurring datasets, the proposed method not only has better deblurring performance in visual perception and quantitative criteria, but also has higher deblurring efficiency.