Image inpainting with deep adaptive generative models for multimedia computing

V. Voronin; N. Gapon; M. Zhdanova; O. Tokareva; E. Semenishchev

doi:10.1117/12.2691343

27 November 2023 Image inpainting with deep adaptive generative models for multimedia computing

V. Voronin, N. Gapon, M. Zhdanova, O. Tokareva, E. Semenishchev

Proceedings Volume 12767, Optoelectronic Imaging and Multimedia Technology X; 127671V (2023) https://doi.org/10.1117/12.2691343
Event: SPIE/COS Photonics Asia, 2023, Beijing, China

Conference Poster

Abstract

Image inpainting is a challenging task where large missing regions must be filled based on the available data. It is an interesting new research topic in multimedia computing and image processing. This paper proposes a novel deep learning reconstruction method using an adaptive generative adversarial neural network (aGAN). The key feature of the proposed network is the dynamic estimation of the trend of the loss function. This estimate finds the optimal balance between adversarial and pixel-by-pixel losses. We introduced the coefficient of the approximating curve, which allows us to estimate the trend dynamics of the loss function. Depending on the value of this curve, we adjust the weight of the pixel-by-pixel loss to make the restored area sharper. The proposed method allows a higher sharpness of the reconstructed area and a more stable learning process. Experiments on the dataset show that our method successfully predicts multimedia information in missing regions and significantly outperforms the state-of-the-art methods.

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

Citation Download Citation

V. Voronin, N. Gapon, M. Zhdanova, O. Tokareva, and E. Semenishchev "Image inpainting with deep adaptive generative models for multimedia computing", Proc. SPIE 12767, Optoelectronic Imaging and Multimedia Technology X, 127671V (27 November 2023); https://doi.org/10.1117/12.2691343

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