Coarse-to-Fine GAN for Image Inpainting via Transformer and Channel-Frequency Encoder
Electronics · 10.04.2026 · 15 (8) · 1580
DOI: 10.3390/electronics15081580 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 10.04.2026. Verfasst von Shibin Wang und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Image inpainting aims to recover missing regions in damaged images while preserving structural coherence and textural authenticity. Although deep learning methods based on generative adversarial networks (GAN) have made significant progress, they still face challenges in modeling long-range dependencies and maintaining semantic consistency, especially when large areas are missing. To address these issues, we propose an innovative multi-stage restoration framework. The coarse restoration stage incorporates attention via a transformer architecture, while the refinement stage introduces a plug-and-play channel-frequency encoder (CF-Encoder). This encoder effectively models both global structure and local details by hierarchically extracting and enhancing features through frequency-domain decomposition combined with an adaptive spatial-channel attention mechanism. Furthermore, we employ a bi-discriminator fusion mechanism to stabilize training and enhance perceptual quality. Experiments across multiple benchmark datasets demonstrate our method’s superior performance in both quantitative metrics and visual fidelity, with particularly notable advantages in high-missing-value scenarios.
Zitieren
APA
Wang, S., Xu, Y., Qin, D., Liu, D., & Li, X. (2026). Coarse-to-Fine GAN for Image Inpainting via Transformer and Channel-Frequency Encoder. Electronics, 15(8), 1580. https://doi.org/10.3390/electronics15081580
Vancouver
Wang S, Xu Y, Qin D, Liu D, Li X. Coarse-to-Fine GAN for Image Inpainting via Transformer and Channel-Frequency Encoder. Electronics. 2026;15(8):1580. doi:10.3390/electronics15081580
BibTeX
@article{Wang2026,
author = {Wang, Shibin and Xu, Yubo and Qin, Dehuang and Liu, Dong and Li, Xueshan},
title = {Coarse-to-Fine GAN for Image Inpainting via Transformer and Channel-Frequency Encoder},
journal = {Electronics},
year = {2026},
volume = {15},
number = {8},
pages = {1580},
doi = {10.3390/electronics15081580}
}
EUVIMED