CTE-Net: Contextual Texture Enhancement Network for Image Super-Resolution
IEEE Transactions on Multimedia · 2024 · 26 · 8000-8013
DOI: 10.1109/tmm.2024.3374576 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2024. Verfasst von Dong Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shaanxi Science Foundation of China, Seed Fund for Creativity and Innovation of Postgraduates of Xi'an University of Technology.
Abstract (Originalsprache)
The object of image super-resolution reconstruction is to overcome the limitations imposed by hardware imaging conditions and patterns, aiming to restore high-frequency details in images through signal processing techniques. Recently, deep learning-based single-image super-resolution reconstruction (SISR) has achieved remarkable performance. However, the current methods exhibit inadequate performance in the reconstruction of texture details, thereby posing a challenge for further enhancing the accuracy of super-resolution reconstruction. In this study, we propose a novel contextual texture enhancement network (CTE-Net) aimed at improving the level of texture details in image super-resolution. The CTE-Net comprises of two crucial components: the multi-level feature aggregation module (MFAM) and the contextual information enhancement module (CIEM). The MFAM integrates global and local low-resolution (LR) features from both the pixel space and channel dimensions, thereby enhancing the feature representation capability of the network. The CIEM is deployed to enhance the network's learning capacity by integrating a meticulously designed context-attention mechanism, which effectively explores the adjacent contextual information of images and thereby amplifies the expressive capability of the generated features. Moreover, we utilize local binary patterns (LBP) to guide the feature selection strategies for MFAM and CIEM, thereby prioritizing the network's decision logic towards the recovery of texture details. The extensive experiments demonstrate that our method yields satisfactory results. In comparison to the state-of-the-art approaches, our method exhibits superior performance on the benchmark datasets.
Förderung
- National Natural Science Foundation of China
- Shaanxi Science Foundation of China
- Seed Fund for Creativity and Innovation of Postgraduates of Xi'an University of Technology
Zitieren
APA
Liu, D., Wang, X., Han, R., Bai, N., Hou, J., & Pang, S. (2024). CTE-Net: Contextual Texture Enhancement Network for Image Super-Resolution. IEEE Transactions on Multimedia, 26, 8000-8013. https://doi.org/10.1109/tmm.2024.3374576
Vancouver
Liu D, Wang X, Han R, Bai N, Hou J, Pang S. CTE-Net: Contextual Texture Enhancement Network for Image Super-Resolution. IEEE Transactions on Multimedia. 2024;26:8000-8013. doi:10.1109/tmm.2024.3374576
BibTeX
@article{Liu2024,
author = {Liu, Dong and Wang, Xiaofeng and Han, Ruidong and Bai, Ningning and Hou, Jianpeng and Pang, Shanmin},
title = {CTE-Net: Contextual Texture Enhancement Network for Image Super-Resolution},
journal = {IEEE Transactions on Multimedia},
year = {2024},
volume = {26},
pages = {8000--8013},
doi = {10.1109/tmm.2024.3374576}
}
EUVIMED