@inproceedings{37bdecb463784b879de3a2284b62acaa,
title = "Image Inpainting Based on High-Order Spatial Interaction Modules",
abstract = "Image inpainting is a fundamental task in the field of computer vision, aimed at using partially visible pixels in an image to repair missing or damaged parts of the image. In this paper, we propose a multi-stage cascaded image inpainting model based on high-order spatial interaction modules, which can achieve input adaption and long-range spatial interaction by introducing recursive gated convolutions in each high-order spatial interaction module, resulting in a global perceptual field and effective modeling of correlation between the inpainted region and the visible image range. Extensive experiments on CelebA-HQ dataset and Paris StreetView dataset demonstrate the effectiveness of the proposed method.",
author = "Jianwu Li and Qihang Hu and Sichun Qin",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024 ; Conference date: 27-07-2024 Through 29-07-2024",
year = "2024",
doi = "10.1109/ICNC-FSKD64080.2024.10702334",
language = "English",
series = "ICNC-FSKD 2024 - 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Maozhen Li and Ning Xiong and Jianguo Chen and Zheng Xiao and Kenli Li and Lipo Wang",
booktitle = "ICNC-FSKD 2024 - 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery",
address = "United States",
}