Time-of-Flight Camera Intensity Image Reconstruction Based on an Untrained Convolutional Neural Network
Round 1
Reviewer 1 Report
Comments and Suggestions for Authorsplease see the attched files
Comments for author File: 
Comments.pdf
Minor editing of English language required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThis manuscript uses a ToF camera as a detector and utilizes its intensity information to apply different reconstruction algorithms for image reconstruction of the object under test. The results show that untrained deep learning algorithms can achieve higher peak signal-to-noise ratios. It was also applied to imaging through scattering media, and the results showed that compared to the original image through scattering media, the reconstructed image had significantly improved noise and contrast.
1. What are the possible sources of noise in the experiment? What is the impact of the increased noise caused by using a total reflection prism TPR in Figure 4 on image reconstruction?
2. How to synchronize triggering between ToF camera and DMD?
3. What are the advantages of ToF cameras as detectors? ToF cameras can obtain intensity and depth information, enabling three-dimensional imaging. This manuscript currently only discusses the application of intensity information, how about depth information?
4. The maximum sampling rate in the experiment mentioned in the article is 37.5%. How does the image reconstruction quality of other algorithms compare to that of DL algorithm when increasing the sampling rate? Will there be other algorithms that obtain higher quality images than DL algorithms?
5. In descriptions such as lines 291-313 and 358-380, it is not necessary to provide obvious data descriptions in the figures. It is recommended to provide relevant textual descriptions highlighting the comparison and analysis of the results.
Comments on the Quality of English LanguageThe quality of English language is fine.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsA solution that combines ToF cameras with single-pixel imaging theory is proposed, applying various reconstruction algorithms to reconstruct the object’s image. Under undersampling conditions, reconstruction approach yields higher peak signal-to-noise ratio compared to the raw camera image, significantly improving the quality of the target object’s image.
However, the experimental design lacks experimental conditions and details.
Comments on the Quality of English LanguageMinor editing of English language required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThe revised Manuscript now can be published in Photonics.
Comments on the Quality of English LanguageMinor editing of English language required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe revision has clarified the concerns, and the changes have helped to improve the paper. The evaluation is convincing.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsAccept after minor revision (corrections to minor methodological errors and text editing)
Comments on the Quality of English LanguageAccept after minor revision (corrections to minor methodological errors and text editing)
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
