Mid-Wave Infrared Snapshot Compressive Spectral Imager with Deep Infrared Denoising Prior

Round 1

Reviewer 1 Report

Dear Authors,

Your manuscript seems to be interesting but with minor changes. Please revise as per the following comments:

1. Abstract and conclusion needs to have validation and calibration results included.

2. Please elaborate results and discussions section with calibration results with numerical results like accuracy, f1-score etc.

3. Modify the format of the paper adding all the theoretical part in materials and methods section instead of explaining wherever is needed.

4. This paper is less than 18 pages which is not an article paper as per the MDPI format. Can you change this paper to technical note or communication paper?

Thank you.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

1. Some more references are required to add, diagram and results are required to more expiations

2.A fair comparative analysis should be included in the results section with the state of art algorithms available in the literature

3.More practical examples are missing in this article.

4. What is the purpose of using KAIST dataset and CAVE dataset. Any other particular reason.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

In this manuscript, the authors propose an MWIR snapshot compressive spectral imager based on a prism and a coded aperture to produce spatio-spectral coded to the benefit of reconstruction. Extensive experiments on both simulation datasets and real infrared scenarios validate the effectiveness of the proposed methods. The manuscript is easy to follow and sounds solid. However, there are some issues to be fixed before publishment.

1. It would be better if the authors could use Mid-wave infrared rather than MWIR for a better understanding.

2. It would be better if the authors could compare their models with some recent works. Only a few of the works mentioned in the manuscript have been published in the recent two years.

3. In Table 1, the authors provided the running time. However, the details of the equipment used for experiments were not provided. Since the type of CPUs and GPUs heavily influence the inference speed, it would be better if the authors could provide more details about the devices for experiments.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf