<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Image inpainting aims to fill the undetectable domain and has been studied using deep learning in recent years. This study investigates smoothness-informed convolutional neural network models for image inpainting. The total variation (TV) is considered and local smoothness constraints are also explored in this study. The local smoothness constraint is conducted by the fidelity of the low-order derivatives on mostly connected parts of the given image at training stage. Unlike most neural network-based inpainting methods using numerous images for training, only a single local image containing the domain to be filled is required for the whole training here. The convolutional neural network accepts the image and is trained using detectable data. Computational results indicate that the local smoothness constraint can conduct a more satisfactory inpainting in comparison to usual TV-based one. We also demonstrate how a deep learning approach is used to solve the Euler-Lagrange equation-based inpainting.</p>
</abstract>

Image inpainting aims to fill the undetectable domain and has been studied using deep learning in recent years. This study investigates smoothness-informed convolutional neural network models for image inpainting. The total variation (TV) is considered and local smoothness constraints are also explored in this study. The local smoothness constraint is conducted by the fidelity of the low-order derivatives on mostly connected parts of the given image at training stage. Unlike most neural network-based inpainting methods using numerous images for training, only a single local image containing the domain to be filled is required for the whole training here. The convolutional neural network accepts the image and is trained using detectable data. Computational results indicate that the local smoothness constraint can conduct a more satisfactory inpainting in comparison to usual TV-based one. We also demonstrate how a deep learning approach is used to solve the Euler-Lagrange equation-based inpainting.

A study of local smoothness-informed convolutional neural network models for image inpainting

University of Science and Technology Beijing

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Image inpainting aims to fill the undetectable domain and has been studied using deep learning in recent years. This study investigates smoothness-informed...

A study of local smoothness-informed convolutional neural network models for image inpainting

Online veröffentlicht: 14. Apr. 2022

Seitenbereich: 897 - 908

Eingereicht: 25. Dez. 2021

Akzeptiert: 10. Apr. 2022

DOI: https://doi.org/10.2478/amns.2022.1.00013

Schlüsselwörter
Smoothness, total variation, convolutional neural network, deep learning, image inpainting

© 2023 Fulian Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

A study of local smoothness-informed convolutional neural network models for image inpainting

Online veröffentlicht: 14. Apr. 2022

Seitenbereich: 897 - 908

Eingereicht: 25. Dez. 2021

Akzeptiert: 10. Apr. 2022

DOI: https://doi.org/10.2478/amns.2022.1.00013

SchlüsselwörterSmoothness, total variation, convolutional neural network, deep learning, image inpainting

© 2023 Fulian Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Smoothness, total variation, convolutional neural network, deep learning, image inpainting