# Restoration of Non-Uniform Motion-Blurred Star Images Based on Dynamic Strip Attention

## TL;DR

This paper introduces a new deep learning method to restore motion-blurred star images, significantly improving image quality and star point recognition.

## Contribution

A novel dynamic strip attention mechanism is proposed for non-uniform motion blur restoration in star images.

## Key findings

- The proposed method achieves a PSNR of 84.08 and SSIM of 0.9928 on simulated datasets.
- Star point recognition accuracy increases by 174% compared to unprocessed images.
- Real-world validation shows a 57% increase in successfully recognized star points.

## Abstract

When capturing star images in long-exposure mode, due to the relative motion between stars and space objects and the observation camera, strip tailings with different directions and lengths will be formed, resulting in a serious decline in image quality and inaccurate centroid positioning. Traditional methods for restoring star images are prone to ringing effects and cannot restore the non-uniformly blurred star images. Aiming at this problem, this paper proposes a star image restoration network based on a dynamic strip attention mechanism. Firstly, a Multi-scale Dynamic Strip Pooling Module is designed to adaptively extract blurred features of different lengths and directions by dynamically adjusting the strip convolution. After that, a Multi-scale Feature Fusion Module is designed to fuse multi-level features to reduce the loss of image details of stars and space objects in the image. Experimental results demonstrate that the proposed method achieves a PSNR of 84.08 and an SSIM of 0.9928 on the 16-bit simulated dataset, outperforming both traditional methods and other deep learning-based approaches. Specifically, the recognition accuracy of star points is increased by 174% in comparison with unprocessed images. Furthermore, this paper validates the network using the real-world dataset spotGEO, and the results indicate that the average number of successfully recognized star points is increased by 57% compared to direct processing of the original images.