Next Article in Journal
Optimization of a Fuzzy System Used to Characterize the Factors That Affect Drivers on Urban Roads
Next Article in Special Issue
A Comparative Study of Safety Zone Visualisations for Virtual and Physical Robot Arms Using Augmented Reality
Previous Article in Journal
A Temporal Transformer-Based Fusion Framework for Morphological Arrhythmia Classification
 
 
Article
Peer-Review Record

Depth-Aware Neural Style Transfer for Videos

by Eleftherios Ioannou * and Steve Maddock *
Reviewer 1:
Reviewer 2:
Submission received: 14 February 2023 / Revised: 16 March 2023 / Accepted: 24 March 2023 / Published: 27 March 2023
(This article belongs to the Special Issue Selected Papers from Computer Graphics & Visual Computing (CGVC 2022))

Round 1

Reviewer 1 Report

This manuscript presents a stylization network to produce stylized videos with improved temporal consistency. The network architecture looks great and the results are also promising. I only have a minor comment as below: 

 

1. In line 207-208, "train with a batch size of 2 for 2 epochs". I would like to confirm with the authors this is not a typo. 2 epochs look too few for a typical neural network training. How would the results look like if more epochs are used? Finally, what hardware was used and how long was the training time? 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

My comments and suggestions are in the attached pdf file. 

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

I would like to thank authors for following my comments and apply them as much as possible. 

Back to TopTop