CGFTNet: Content-Guided Frequency Domain Transform Network for Face Super-Resolution
Information · 02.12.2024 · 15 (12) · 765
DOI: 10.3390/info15120765 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 02.12.2024. Verfasst von Yeerlan Yekeben und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific and Technological Innovation 2030 Major Project, Key Laboratory Open Projects in Xinjiang Uygur Autonomous Region.
Abstract (Originalsprache)
Recent advancements in face super resolution (FSR) have been propelled by deep learning techniques using convolutional neural networks (CNN). However, existing methods still struggle with effectively capturing global facial structure information, leading to reduced fidelity in reconstructed images, and often require additional manual data annotation. To overcome these challenges, we introduce a content-guided frequency domain transform network (CGFTNet) for face super-resolution tasks. The network features a channel attention-linked encoder-decoder architecture with two key components: the Frequency Domain and Reparameterized Focus Convolution Feature Enhancement module (FDRFEM) and the Content-Guided Channel Attention Fusion (CGCAF) module. FDRFEM enhances feature representation through transformation domain techniques and reparameterized focus convolution (RefConv), capturing detailed facial features and improving image quality. CGCAF dynamically adjusts feature fusion based on image content, enhancing detail restoration. Extensive evaluations across multiple datasets demonstrate that the proposed CGFTNet consistently outperforms other state-of-the-art methods.
Förderung
- Scientific and Technological Innovation 2030 Major Project
- Key Laboratory Open Projects in Xinjiang Uygur Autonomous Region
Zitieren
APA
Yekeben, Y., Cheng, S., & Du, A. (2024). CGFTNet: Content-Guided Frequency Domain Transform Network for Face Super-Resolution. Information, 15(12), 765. https://doi.org/10.3390/info15120765
Vancouver
Yekeben Y, Cheng S, Du A. CGFTNet: Content-Guided Frequency Domain Transform Network for Face Super-Resolution. Information. 2024;15(12):765. doi:10.3390/info15120765
BibTeX
@article{Yekeben2024,
author = {Yekeben, Yeerlan and Cheng, Shuli and Du, Anyu},
title = {CGFTNet: Content-Guided Frequency Domain Transform Network for Face Super-Resolution},
journal = {Information},
year = {2024},
volume = {15},
number = {12},
pages = {765},
doi = {10.3390/info15120765}
}
EUVIMED