Interactive Holographic Display System Based on Emotional Adaptability and CCNN-PCG

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper presents an innovative holographic display system with emotional adaptability and a novel CCNN-PCG algorithm. It integrates advanced AI models (e.g., ChatGLM, LLMs), image processing, and holography to create an interactive 3D digital human interface. The paper shows promise for immersive displays, digital avatars, and future HCI applications. Following are some comments:

• Kindly rearrange all figure citations so they appear in the order they are first mentioned in the text (e.g., “Figure 1,” then “Figure 2,” etc.). Ensure all figures and tables are explicitly referenced in the main body before they appear.
• In abstract, clarify the novelty and contribution more succinctly.
• Authors should include a block diagram or flowchart showing how point cloud data flows through the CCNN-PCG pipeline. Also, provide a table comparing CCNN vs standard CNN architectures used in holography.
• Paper should explain why complex-valued networks are particularly suitable for phase preservation in holography.
• Describe how Open3D + Poisson sampling improves upon previous depth camera-based systems.
•  

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

We would like to thank you for submitting your manuscript to our journal. This paper presents an interactive holographic display system that integrates an emotional adaptability module with a novel Complex-Valued Convolutional Neural Network Point Cloud Gridding (CCNN-PCG) algorithm. The work aims to address critical challenges in holographic display, including computational efficiency, reconstruction quality, and the naturalness of human-computer interaction. The proposed framework, which combines 2D-to-3D model generation, LLM-powered voice interaction, and an efficient hologram generation algorithm, demonstrates promising results in both speed and visual quality through simulations and optical experiments.

However, there are still the following problems in this paper that need further improvement:

1、Response to Previous Review: First and foremost, it is crucial that the authors thoroughly address all points raised in the previous round of reviews. Ensuring that all prior feedback has been incorporated is a prerequisite for the current review to proceed effectively.

2、Insufficient Quality of Figures: A significant issue throughout the manuscript is the poor quality of the figures. Specifically, the core experimental results presented in Figure 6 and Figure 7 are blurry and have a low resolution. This makes it extremely difficult for reviewers and readers to clearly see the details of the digital human models, assess the quality of the generated actions, and verify the paper's claims about visual fidelity. To properly substantiate the results, it is essential that the authors replace these, and all other unclear figures, with high-resolution, clearly legible versions.

3、Lack of Clarity in Architectural Diagrams: The network architecture diagrams, such as Figure 3 and Figure 5, provide a helpful overview but could be significantly improved in terms of clarity. It is recommended that the authors add brief but clear summaries of the network’s workflow and data flow directly within the figure captions or as annotations on the diagrams themselves. This would help readers more intuitively grasp the function of each component and the overall process without needing to hunt for scattered explanations in the main text.

4、Inconsistent Formatting of Equations: For better readability and adherence to standard academic publishing formats, all mathematical equations throughout the manuscript (e.g., Equations 1-7) should be center-aligned. While a minor point, consistent formatting is important for the professionalism and final presentation of the manuscript.

5、More extensive experimental validation is needed: the current experimental section provides a good proof of concept, but its scope is limited. To more robustly demonstrate the effectiveness and quality of the proposed interactive system, the inclusion of a wider range of experiments would be of high value. For example, to present more diverse and complex interaction scenarios. Furthermore, to better demonstrate the contribution of each component in the framework, you can take inspiration from the design of experiments in related fields. For example, the TPDNet paper on 3D object detection effectively uses ablation studies to demonstrate the specific contribution of each of its key network components to the final performance.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

This paper proposes a holographic voice-interactive display system incorporating speech interaction and holographic modules. Generally, this research is interesting and meaningful; however, the paper needs improvement in its presentation. Here are a few comments from my side:

1. The abstract section should include the manuscript's novelty problems.
2. This paper concentrates on image processing; some recent interesting results deserve to be mentioned, e.g., 10.1016/j.heliyon.2024.e37072; 10.1504/IJBM.2024.140771.
3. In the introduction section, the description of the main contributions is brief and not specific enough.
4. There are plenty of abbreviations throughout, and a summary should be added.
5. Some sentences are expressed unreasonably, for example, “...This research pioneers novel methodologies…”
6. Some typos exist in the full text, e.g., Figure 1 is not cited, and in Fig.7, (d) is incorrectly written as (b); please check it.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

This paper proposes a holographic voice-interactive display system incorporating 399 speech interaction and holographic modules. To improve the quality of this manuscript, my comments and suggestions are listed as follows.

1. This is the V1 version. Why are there some annotations in this manuscript?
2. The title is very long. Authors should rewrite it to make it concise.
3. For Section Abstract, it is very short. Authors can rewrite and expand it, especially for the method description.
4. At 140th line of Page 4, Figure 3 should be Figure 1.
5. Most of the figures are very fuzzy, such as Figure 1. Authors should repot them.
6. In this manuscript, authors give the four core modules of the holographic voice-interactive display system. However, the description for these modules is very simple.
7. In Figure 1, “Step 1, Step 2, Step 3, Step 4” should be “Modules 1, Modules 2, Modules 3, Modules 4”.
8. For Section 3, authors are suggested to divide the content into some subsections according to the evaluation indexes.
9. In Abstract, authors state that CCNN-PCG improves reconstruction quality while increasing computational 16 speed by over 200%. But I cannot find the data in the whole paper.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Comments to the Author

Thank you for submitting the revised manuscript and for your efforts in addressing the previous suggestions. The paper has shown improvement. However, we believe that significant revisions are still required concerning the rigor of the argumentation and the standardization of the manuscript before it can meet the standards for publication. The main suggestions are concentrated in two areas: first, issues with the manuscript's language details and terminological consistency; and second, the depth and breadth of the experimental validation, particularly regarding the rigor of the ablation study and the generalizability of the results.

Detailed suggestions for these two areas are as follows:

1、We recommend a comprehensive proofread of the manuscript to correct minor grammatical and spelling errors and to ensure the consistency of key abbreviations. For example, the term "CCNN-PCG" used in the main text should be unified with "PCG-CCN" used in the tables , and the phrase "Text to pint cloud" in Figure 4 should be corrected, etc.

2、To further enhance the persuasiveness of the experimental validation, we recommend a deeper investigation in the experimental section. We acknowledge the author's approach of demonstrating the new module's contribution by comparing CCNN-PCG with the basic PCG algorithm; however, this does not constitute a rigorous ablation study. To more robustly justify the necessity and rationale of the model's components, we recommend conducting a more formal ablation study: systematically remove or replace a key component from the final CCNN-PCG model and quantitatively analyze its impact on performance. (You may draw inspiration from experimental designs in related fields. For instance, the TPDNet paper on 3D object detection effectively uses ablation studies to demonstrate the specific contribution of each of its key network components to the final performance.) Furthermore, to better substantiate your claim of enhanced holographic quality, we suggest you demonstrate a more diverse range of experimental results. The current results are primarily focused on a few characters; we recommend adding holographic characters of different shapes, postures, or genders as new experimental subjects to prove that your method's effectiveness is not an isolated case but has broad applicability.

Therefore, I would like to give a "Major Revision" recommendation.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

This paper is fascinating and challenging. It is also well-organized and well-written. In my opinion, it deserves publication in the journal.

Author Response

Thank you very much for your positive review and kind words regarding our manuscript.

Reviewer 4 Report

Comments and Suggestions for Authors

Authors have carefully revised their manuscript according to my comments and suggestions. I am satisfied with their revisions. However, authors should pay attention to the following issues before the formal publication.
(1) Some figures are very fuzzy, such as Fig. 1 and Fig. 8.
(2) Tab.1 is not the three-line table.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 3

Reviewer 2 Report

Comments and Suggestions for Authors

Please find an attachment.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf