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.
Dear authors, we are pleased to verify that you meet the reviewer's valuable feedback to improve your research.
Thank you for considering PeerJ Computer Science and submitting your work.
[# PeerJ Staff Note - this decision was reviewed and approved by Xiangjie Kong, a PeerJ Section Editor covering this Section #]
This is a revised manuscript, The quality is improved after revision, It can be accepted.
The method is good, and the experiments are sufficient.
A novel FR image quality assessment method is proposed.
none.
well written
well written
well written
The author has addressed all of my concerns. At this stage, I recommend accepting this manuscript for publication.
The authors addressed to my questions; I propose that all of the answers be thoroughly considered during the article discussion session. However, the paper still need figure and table adjustments.
The authors addressed to my questions; I propose that all of the answers be thoroughly considered during the article discussion session. However, the paper still need figure and table adjustments.
The authors addressed to my questions; I propose that all of the answers be thoroughly considered during the article discussion session. However, the paper still need figure and table adjustments.
The authors addressed to my questions; I propose that all of the answers be thoroughly considered during the article discussion session. However, the paper still need figure and table adjustments.
Dear authors,
You are advised to critically respond to all comments point by point when preparing a new version of the manuscript and while preparing for the rebuttal letter. Please address all the comments/suggestions provided by the reviewers.
Reviewer 1 has requested that you cite specific references. You may add them if you believe they are especially relevant. However, I do not expect you to include these citations, and if you do not include them, this will not influence my decision.
Kind regards,
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors agree that they are relevant and useful.
**PeerJ Staff Note:** Please ensure that all review and editorial comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Alternatively, you should make your own arrangements to improve the language quality and provide details in your response letter. – PeerJ Staff
PCoelho
This paper proposes a full reference stereoscopic image quality assessment method by using monocular and binocular features. Experimental results on LIVE 3D IQA database demonstrate the effectiveness of the proposed metric. However, I would suggest a major revision before this work can be considered for publication. I hope the follow comments will help the authors to improve this manuscript.
Some figures (e.g., Figure 1, Figure 2 and Figure 6) in this manuscript are unclear, it is suggested to improve the quality of these figures.
In this paper, the description of the manuscript is suggested to be expressed in the general tense instead of the past tense. Besides, the word “suggested” in line 17 should be replaces by “propose or develop”. Please read more high-quality papers (e.g., IEEE TIP, TMM)to enhance the description.
The limitations of the proposed method should be clearly discussed.
It is necessary to validate the computational complexity of the proposed metric, please add a comparative experiment to evaluate the run-time of feature extraction in terms of different IQA methods.
1. The presentation of manuscript is very important for readers and other researchers. I encourage the authors to have their manuscript proof-edited by a fluent English speaker to improve the level of paper presentation.
2. Some specific academic vocabulary in the manuscript are mistranslated, for example the description “stereo picture” in lines 23, 68, “single and binocular features” in lines 529, 534. They should be replaced by “stereo image” , “monocular and binocular features”, please check the full manuscript.
3. In lines 82-84 of this manuscript, we feel puzzle by this description. Is this the third contribution of this manuscript? Please confirm.
4. In this manuscript, only some stereo IQA methods have been reviewed, it is suggested to review some recently-developed IQA papers in the section of introduction, such as: doi: 10.1109/TMM.2023.3330096, doi: 10.1109/TIM.2023.3306527, doi: 10.1109/TMM.2023.3338412.
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors agree that they are relevant and useful.
1. The English expression is not sufficiently standardized and needs refinement to further enhance the accuracy and standardization of the manuscript's presentation.
2. The references cited in the Introduction section are too old. It is recommended to use literature from the past three years for the review analysis.
3. The clarity of the Figures in the manuscript is low and needs revision.
1. It is suggested to further elaborate on the motivation of this manuscript's research in the Introduction section, in order to introduce the novelty of this manuscript.
1. The author introduced many deep learning-based no-reference methods in the related work and mentioned, 'While some deep learning-based NR-SIQA methods have achieved promising results in the literature, they often come with high training time complexity, resulting in lengthy processing times for generating results.' Therefore, it is suggested that the author add time complexity comparison experiments in the experimental section to further demonstrate the advancement of the proposed method.
The authors suggested a full reference stereo quality assessment metric based on earlier no-reference approaches. The measure is based on the cyclopean hypothesis, which takes into account binocular rivalry issues. In my opinion. The manuscript has the potential to be published following some revisions. I appreciate that the authors provided the implementation code.
- A cross-validation experiment is needed for better comparison.
- The authors address the issue of binocular rivalry, although symetric/asymetric evaluation is missing from the experimental results.
- Please discuss why the proposed metric performed well on LIVE II but poorly on LIVE I.
- Ablation tests are needed to evaluate the effectiveness of monocular and binocular feature extraction.
- The introduction and related work are mixed up. I respectfully advise combining the two sections into one.
- The introduction/related work requires significant improvement to include more recent studies and explore the issue of binocular rivalry.
- Figures are difficult to follow because to extreme compression and incorrect layout.
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.