Multi-Scale Aggregation Residual Channel Attention Fusion Network for Single Image Deraining
Round 1
Reviewer 1 Report
The paper presents an interesting idea to analyze an image during rainy days. However, there are some parts that I would suggest the Author improve it. They are:
1. Please amend the word "Chapter" as it is not a master's or Ph.D. thesis.
2. Please improve the Figures' resolution especially Figures 1 and 2. The Authors could provide a zoom-in for selected Figures in Figure 2 for more information to the reader.
3. The paper used datasets from [31] and [39], in my opinion, the Authors should provide more description of these datasets. Why there are no train samples for RAIN100H and RAIN800?
4. Authors conducted the method comparison as presented in Table 2. Prior to the performance results, it would be better to provide the parameters setup for these methods. It is to provide a fair comparison.
5. Regarding Figures 8 and 9, the Authors should find a quantitative performance comparison to support the presented results in Figures 8 and 9. What the Authors are trying to say with the blue and red box? In addition, what are the differences between one image (or methods) with other images (or methods)?
Author Response
Please refer to the attached revise file for more details.
Author Response File: 
Author Response.docx
Reviewer 2 Report
1. review of some more recent papers can be added.
2. Clarity of each figure can be improved.
3. Statistical analysis of the result can be carried out to get more clarity on the output of the model.
Author Response
Please refer to the attached revise file for more details.
Author Response File: Author Response.docx
Reviewer 3 Report
This paper proposes a multi-scale aggregation residual channel attention fusion network for single image deraining and achieves good results. I recommend this manuscript for publication after the authors clearly explain the following issues.
1. What are the problems with the methods of Fu, Li, Wang, Ren, Jiang, Zamir, Yin?
2. The RCA block in Figure 1 is not drawn.
3. AS、AM、AL in the paper is not explained.
4. There is a problem with the definition of formula (2) in line 272 of the article.
5. CONCLUSIONS needs more in it, as it's more of an afterthought. The authors are suggested to highlight important findings and include afterthought of this work.
6. The format of the article should be further improved.
7. Some sentences have grammatical errors, the meaning of the sentences is not clear, and the coherence of some sentences is not strong.
Author Response
Please refer to the attached revise file for more details.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Dear Authors,
Thank you for the effort in revising the paper. I have no further comments after checking the Authors' response document.
- Reviewer -
Author Response
Please refer to the attached revise file for more details.
Author Response File: Author Response.docx
Reviewer 3 Report
The font and size of the caption of the sub-figure in Figure 2 should be uniform.
Author Response
Please refer to the attached revise file for more details.
Author Response File: Author Response.docx
