DLALoc: Deep-Learning Accelerated Visual Localization Based on Mesh Representation
Round 1
Reviewer 1 Report
The work is not compelling due to its lack of writing, formulas, figures, graphs, equations, and tables. They are mentioned throughout the text.
Author Response
Thank you for your comments on my manuscript, please see the attachment for my response to the comments.
Author Response File: Author Response.docx
Reviewer 2 Report
Comments for author File: Comments.pdf
Author Response
Thank you for your comments on my manuscript, please see the attachment for my response to the comments.
Author Response File: Author Response.docx
Reviewer 3 Report
This paper is written well and interests to the readers. The proposed framework and algorithm are represented in an elaborate manner and discussed in detail.
1. The number of references can be increased.
Author Response
Thank you for your comments on my manuscript.
I added more references on line 87 about localization using deep learning, including using deep learning for feature matching, or directly using deep learning for pose estimation.
Reviewer 4 Report
The article "DLALoc: Deep-Learning Accelerated Visual Localization Based on Mesh Representation" proposes a novel framework called deep-learning accelerated visual localization based on mesh representation. In this reviewer’s opinion, the paper needs improvements.
- Please insert the computational platform where the results were obtained.
- Insert the unit for the time in Table 3.
Author Response
Thank you for your comments on my manuscript, please see the attachment for my response to the comments.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
The suggested modifications were made entirely, so I consider it well done, Note. the markings made outside of these appear in the document, everything is fine.
Author Response
Thank you for your comments and reminder, please see the attachment for my response to the comments.
Author Response File: Author Response.docx