Parallel Edge-Image Learning for Image Inpainting

Page view(s)
47
Checked on Nov 30, 2024
Parallel Edge-Image Learning for Image Inpainting
Title:
Parallel Edge-Image Learning for Image Inpainting
Journal Title:
2022 IEEE International Conference on Multimedia and Expo (ICME)
Keywords:
Publication Date:
26 August 2022
Citation:
Hu, J., Wang, C., Zhang, Y., Liu, L., Yin, Y., & Zimmermann, R. (2022). Parallel Edge-Image Learning for Image Inpainting. 2022 IEEE International Conference on Multimedia and Expo (ICME). https://doi.org/10.1109/icme52920.2022.9859715
Abstract:
The primary goal of image inpainting is to fix holes in a damaged image with natural contents. A key challenge is that a damaged image contains complex structures in different ways, with each consisting of its configuration of edges and spatial dependencies. As a result, filled images often converge to unnatural and implausible results. Currently, the edge-image inpainting methods adopt two stages to recover edges and images successively, which suffer from feature inconsistency and error accumulation. This leads us to present a parallel edge-image learning framework that explicitly characterizes these internal configurations in a single stage. The framework introduces a dual parallel network-based decoder to generate the image and the edges concurrently, leading to feature consistency at the semantic level. Also, a new crossfire mechanism aims to exchange edge-image information in the decoder, avoiding error accumulation. Empirical evaluations on benchmark datasets suggest that our approach outperforms the state-of-the-art methods on image inpainting.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Ministry of Education - Academic Research Fund Tier 1
Grant Reference no. : T1 251RES2029

National Major Science and Technology Projects of China (grant no. 2018AAA0100703), the National Natural Science Foundation of China (grant nos. 61977012)
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1945-788X
Files uploaded:

File Size Format Action
image-inpainting-icme.pdf 1.21 MB PDF Open