Image Inpainting Network Based on Deep Fusion of Texture and Structure

Huilai Liang, Xichong Ling, Siyu Xia

2023

Abstract

With the recent development of deep learning technique, automatic image inpainting has gained wider applications in computer vision and has also become a challenging topic in image processing. Recent methods typically make use of texture features in the images to make the results more realistic. However this can lead to artifacts in the processed images, one of the reasons for this is that the structural features in the image are ignored. To address this problem, we propose an image inpainting method based on deep fusion of texture and structure. Specifically, we design a dual-pyramid encoder-decoder network for preliminary fusion of texture and structure. A layer-by-layer fusion network of texture and structure is applied to further strengthen the fusion of texture and structure feature afterwards. In order to strengthen the consistency of texture and structure, we construct a multi-gated feature merging network to achieve a more realistic inpainting effect. Experiments are conducted on the CelebA and Place2 datasets. Qualitative and quantitative comparison demonstrate that our model outperforms state-of-the-art models.

Paper Citation

in Harvard Style

Liang H., Ling X. and Xia S. (2023). Image Inpainting Network Based on Deep Fusion of Texture and Structure. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 147-155. DOI: 10.5220/0011718100003411

in Bibtex Style

@conference{icpram23,
author={Huilai Liang and Xichong Ling and Siyu Xia},
title={Image Inpainting Network Based on Deep Fusion of Texture and Structure},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={147-155},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011718100003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Image Inpainting Network Based on Deep Fusion of Texture and Structure
SN - 978-989-758-626-2
AU - Liang H.
AU - Ling X.
AU - Xia S.
PY - 2023
SP - 147
EP - 155
DO - 10.5220/0011718100003411