Multi-Scale Aggregation Stereo Matching Network Based on Dense Grouping Atrous Convolution
Round 1
Reviewer 1 Report
The authors propose a Multi-Scale Aggregation Stereo Matching Network based on Dense Grouping Atrous Convolution. Some more specific comments are listed below:
1. The abstract should be restructured. The abstract not only briefly explains the research objective but also briefly states the main results and the main conclusions. How accurately did the DenseGASPP model predict?
2. Create a more detailed literature review in the introduction. Present the novelty more clearly and in the context of the existing literature.
3. The article summarizes the study's results but does not provide context for the findings (there is no detailed discussion). I strongly recommend that the authors discuss the difference between their work and the studies previously conducted in the literature.
4. I recommend adding the Conclusions section because you can highlight your work's significance too much. You can also pay more attention to the results
5. What were the limitations of the study? I suggest including a separate section to discuss the limitations of the proposed work and the future research directions.
Generally, the manuscript is interesting for readers of this journal, and I hope my comments can help to improve the quality of the manuscript.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
The work of the authors is based on previous work they conducted. In general, it is an interesting proposal, even if it is not a totally novel idea.
Following, we propose some suggestions for improve the quality of the manuscript.
The references seem not updated; numerous cited works are quite old. Some recent works such as:
Zhu, Zhidong, et al. "Multi-scale cross-form pyramid network for stereo matching." 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA). IEEE, 2019.
Zhu, Ziyu, et al. "MPANet: Multi-Scale Pyramid Aggregation Network For Stereo Matching." 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2021.
Are not named at all, even if can be compared with the proposed work. Moreover, in those papers, the same dataset is used (Scene Flow, KITTI). Thus, we invite the authors to introduce them in the study, or even others, for comparing their results with some of the most advanced techniques in the state-of-the-art.
There are some typos. Moreover, some sentences can be improved due to some repetitions (e.g., line 113) or informal/partially incorrect expressions (e.g., line 118 "amount"). We suggest the authors to correct them.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Accept in present form
Reviewer 2 Report
The final changes to the document complete the missing events highlited in the first review. Due to this fact, the manuscript could be published as is.
