Real image improvement study based on pivotal tuning inversion

Xinyue Niu; Yixuan Zhou; Zhaoyuan Gong

doi:10.1117/12.3027128

1 April 2024 Real image improvement study based on pivotal tuning inversion

Xinyue Niu, Yixuan Zhou, Zhaoyuan Gong

Author Affiliations +

Proceedings Volume 13077, Fourth International Conference on Signal Processing and Machine Learning (CONF-SPML 2024); 130770G (2024) https://doi.org/10.1117/12.3027128
Event: 4th International Conference on Signal Processing and Machine Learning (CONF-SPML 2024), 2024, Chicago, IL, United States

Abstract

In recent years, facial editing technology using style-gan has developed rapidly. This takes advantage of StyleGAN's powerful generator, but it still presents some problems in practical applications that have been widely identified and proposed solutions. PTI(Pivotal Tuning Inversion) is a technique to optimize generators, which was released in 2021 and is a relatively new method with good effects. But in the actual test, there are still some problems. In this work, two significant flaws regarding PTI were found when it was applied to editing human faces. It is confirmed that this negative effect is widespread and non-negligible in some cases. Following the original paper of PTI, this paper specifically investigates how these defects occur from two aspects. A method of tuning hyperparameters is raised to improve the output inversion image. In the end, a conjecture is proposed that a discriminator could be trained to help the machine learn human preferences, an approach that has the potential to minimize the impact due to feature loss.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xinyue Niu, Yixuan Zhou, and Zhaoyuan Gong "Real image improvement study based on pivotal tuning inversion", Proc. SPIE 13077, Fourth International Conference on Signal Processing and Machine Learning (CONF-SPML 2024), 130770G (1 April 2024); https://doi.org/10.1117/12.3027128

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Gallium nitride

Image quality

Skin

Data modeling

Machine learning

Convolution

Show All Keywords

Keywords/Phrases

Search In:

Publication Years