An integrated CycleGAN-Diffusion approach for realistic image generation

Boyan Liu; Jiayi Ji; Liuqing Gu; Ziheng Jiang

doi:10.1117/12.3027121

1 April 2024 An integrated CycleGAN-Diffusion approach for realistic image generation

Boyan Liu, Jiayi Ji, Liuqing Gu, Ziheng Jiang

Proceedings Volume 13077, Fourth International Conference on Signal Processing and Machine Learning (CONF-SPML 2024); 130770C (2024) https://doi.org/10.1117/12.3027121
Event: 4th International Conference on Signal Processing and Machine Learning (CONF-SPML 2024), 2024, Chicago, IL, United States

Abstract

Cycle-Consistent Adversarial Network (CycleGAN) has been pivotal for image style transfer with the realm of computer vision. However, the quality of CycleGAN’s output often lacks fine-grained details when generating realistic images. Therefore, this paper proposes a realistic image generation approach based on an integrated CycleGAN-Diffusion network to achieve higher image quality with a comparative small model. To evaluate the Diffusion model’s ability to produce high-fidelity images under resource constraints and to compare its image quality with datasets processed using CycleGAN, we apply irregular masks with Gaussian noise during the inpainting and restoration phases. For assessing sample fidelity, we utilizes Mean Squared Error (MSE), Inception Score (IS) and Fréchet inception distance (FID) in this paper. Through extensive experiments, the proposed network is proved to perform better in generating high fidelity images, helping us to achieve FID scores of 5.98 and IS scores of 8.34 at 160×160 resolutions in the process of restoration and achieve IS scores of 7.69 in the inpainting process, both outperforming previous CycleGAN.

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

Citation Download Citation

Boyan Liu, Jiayi Ji, Liuqing Gu, and Ziheng Jiang "An integrated CycleGAN-Diffusion approach for realistic image generation", Proc. SPIE 13077, Fourth International Conference on Signal Processing and Machine Learning (CONF-SPML 2024), 130770C (1 April 2024); https://doi.org/10.1117/12.3027121

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
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image quality

Diffusion

Education and training

Data modeling

Image processing

Image segmentation

Gallium nitride

Show All Keywords

Keywords/Phrases

Search In:

Publication Years