Multi-Level Convolutional Network for Ground-Based Star Image Enhancement

Round 1

Reviewer 1 Report

Comments for author File: Comments.pdf

See attached file

Author Response

Dear referee:

Thank you very much for your comments and suggestions, your affirmation is the biggest support and encouragement to me. I have revised and improved the paper according to your suggestions. The specific content and explanation of each suggestion will be described in detail in the submitted file.

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Here are some suggestions to improve the quality of this article. The article proposes a new star map enhancement algorithm called MBS-Net based on background suppression. Specifically, the network consists of three parts: background information estimation, multi-level U-Net cascade module, and recursive feature fusion. The effectiveness of this method is validated on four datasets, and although the innovation is weak, the work is detailed, logically clear, and rich in experiments.

1. The data should be made available as soon as possible.
2. It is recommended to supplement the review of transformer because its characteristics are highly beneficial for background modeling and global modeling. Here are some possible references to consider:

• Building extraction from remote sensing images with sparse token transformers.
• Star: A structure-aware lightweight transformer for real-time image enhancement
• Continuous remote sensing image super-resolution based on context interaction in implicit function space.
• U-shape transformer for underwater image enhancement

3. Downstream tasks, such as object detection results, should be added to the experiment to compare images before and after enhancement. It is important to ensure that the target box annotation is absolutely accurate.
4. The best metrics in the experimental table should be highlighted in bold.
5. The number of references cited is insufficient, and some references lead to "Error! Reference source not found."
6. "some noise in an image that has a greater impact on the im-140 age, they should be given a higher weight" - it is unclear whether higher weight should be used for suppression or activation. This should be clarified in the text.

No problem

Author Response

Dear referees:

         We gratefully appreciate for your valuable suggestions and guidance, and thanks very much for giving us an opportunity to revise our manuscript. your affirmation is the biggest support and encouragement to us. We have revised and improved the thesis accordingly according to your suggestions. The specific content and explanation of each suggestion will be described in detail in the submitted file.

Please see the attachment.

Author Response File: Author Response.docx