All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
The paper has been revised sufficiently and is ready to go for publication.
[# PeerJ Staff Note - this decision was reviewed and approved by Xiangjie Kong, a PeerJ Section Editor covering this Section #]
The authors have addressed all the questions I have mentioned. I have no further questions.
The strong aspect of the paper is the authors show that the proposed technique to achieve better quality processing than the enhancement methods.
All underlying data have been provided.
n/a
Thanks for your interest in the journal. I look forward to your revised version with an explanation of how you addressed the first reviewer's comments.
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
This paper studies the problem of underwater image enhancement. The main idea is using deep learning based on dual attention fusion model. This idea is not sufficiently novel, because the authors only adopted this model and introduced perceptual loss function for improved visual perception. The strong aspect of the paper is the authors show that the proposed technique to achieve better quality processing than the enhancement methods.
I have the following problems with this paper:
- The innovation of this paper is not clear, and it is difficult for readers to understand the main contributions of this paper. The Introduction can be revised to emphasize the main contribution of the work.
- The article has a poor organization: the quality of illustrations can be improved; it is necessary to include a block diagram explaining the proposed algorithm.
- In using formulas for the detailed explanation, this article does not explain all the letters involved; please pay attention to the letter interpretation.
- The proposed fitness function needs to be described in more experiment detail too.
- The authors did not a present full objective quality comparison on test images to check the quality of their enhancement methodology. The methodology of using full reference measures (SSIM, PSNR) more suitable for image denoising problem. I recommend presenting an estimation of non-reference measures whit more specified for image enhancement (for example, AME, EMEE, SDME, Visibility, TDME, BIQI, BRISQUE, ILNIQE).
- Several technical information and details about computation costs are required.
- For the experiments, some discussion should be given about the results to explain the merits and drawbacks of the proposed method.
no comment
This article is written in professional English. Expressions are clear and unambiguous. Ample background works are provided.
As the research question is well-define, they introduce the proposed architecture clearly. They also did a very extensive experiment and obtain very promising results in multiple quality evolution measures.
Authors presented a dual attention fusion Transformer for underwater image enhancement. According to the results of experiments, it is validated that the proposed architecture improves the quality of underwater images and outperforms most of the compared algorithms. They also proposed a synthesized underwater image dataset, which contains images of various water types.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.