Research on High-Resolution Face Image Inpainting Method Based on StyleGAN

Round 1

Reviewer 1 Report

In this work, the authors proposed a framework for face recognition in images. The framework uses ResNet to predict the latent vector of the image, then generate the face image through the pre-trained StyleGAN model. The authors used CelebA-HQ data-set to evaluate the performance of proposed framework.

Overall, the paper is well written and organized, however, I have following concerns the authors need to consider:

1. The contribution of the work is not clear. The authors need to explicitly mention what are the gaps left by the previous approaches and how proposed framework filled those gaps.
2. Experiment section is weak. The authors need to performance more quantitative and qualitative comparisons with other reference methods.
3. What is time complexity of proposed framework? What is the response time of recognition?
4. What is the number of parameters in the proposed framework?
5. The authors need to discuss the failure cases

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The information presented in this article is useful, research contribution is satisfactory. However, the following suggestions are recommended:

• Your abstract does not highlight the specifics of your research or findings. Rewrite the Abstract section to be more meaningful. I suggest: problems, Aim, Methods, Results, and Conclusion.
• In result and discussion, the weakness of the study is that the results were only scantily discussed and compared with the findings of other authors. The Practical application section is too general. It lacks recommendations or information on the new insights provided by the study.
• The conclusion at the end of this section should be improved. Conclusions should be amended to incorporate a broader discussion of the significance and potential application of this specific study.
• The Limitations of the proposed study need to be discussed before conclusion.
• Finally, it should be mentioned that there are so many scientific and grammatical errors in the text, it is suggested to revise the manuscript text carefully.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have addressed my concerns

 

Thanks

Author Response

We did our best to correct grammatical and spelling errors in the manuscript , and some errors were found and corrected. Thank you very much for all your comments on the manuscript.

Reviewer 2 Report

The authors have significantly improved the quality of the manuscript and the presentation of results. They have satisfactorily attended to all the reviewer's comments. Hence the manuscript can be accepted.

Author Response

We did our best to correct grammatical and spelling errors in the manuscript , and some errors were found and corrected. Thank you very much for all your comments on the manuscript.