Defocus-enhanced technique for real-world scenarios using generative models

Yuhao Li; Wenkang Gong; Tianle Li; Jiaqing Dong; Xianlin Song

doi:10.1117/12.3007254

13 December 2023 Defocus-enhanced technique for real-world scenarios using generative models

Yuhao Li, Wenkang Gong, Tianle Li, Jiaqing Dong, Xianlin Song

Proceedings Volume 12942, First Advanced Imaging and Information Processing Conference (AIIP 2023); 129420F (2023) https://doi.org/10.1117/12.3007254
Event: 1st Advanced Imaging and Information Processing, 2023, Jinggangshan, China

Abstract

In recent years, significant progress has been made in deep learning-based image deblurring. These approaches utilize deep neural networks to learn the map between blurry and clear images or jointly learn the blurry kernel and clear image. They have demonstrated effectiveness in enhancing image quality, preserving details, and handling various types and degrees of blur. The objective of this study is to develop a defocus enhancement technique for real-world scenarios using score-based generative models. Stochastic differential equations (SDE) are employed to gradually introduce noise, thereby smoothing the data distribution towards a known prior distribution. The Score-Matching Langevin Dynamics (SMLD) model estimates the score for each noise scale, while Diffusion Models (DDPM) train the target model for score computation. This process constructs a score-based model capable of reversing the SDE over time. A predictor-corrector framework corrects the evolution of the reverse-time SDE, and the prior distribution is transformed back to the data distribution by removing the noise. By leveraging score-based generative models, accurate score estimation and sample generation are achieved using neural networks and numerical SDE solvers. This technique effectively restores clarity and details in defocused images, thereby enhancing overall image quality.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yuhao Li, Wenkang Gong, Tianle Li, Jiaqing Dong, and Xianlin Song "Defocus-enhanced technique for real-world scenarios using generative models", Proc. SPIE 12942, First Advanced Imaging and Information Processing Conference (AIIP 2023), 129420F (13 December 2023); https://doi.org/10.1117/12.3007254

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
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image quality

Autoregressive models

Image enhancement

Image processing

Statistical modeling

Diffusion

Image restoration

Show All Keywords

Keywords/Phrases

Search In:

Publication Years