Oeinr-rfh: Outlier elimination based iterative neighbor representation for robust face hallucination
To make the face hallucination process robust to impulse noise, a new outlier elimination
based iterative neighbor representation (OEINR) algorithm is proposed in this work. The …
based iterative neighbor representation (OEINR) algorithm is proposed in this work. The …
Implicit Mutual Learning With Dual-Branch Networks for Face Super-Resolution
K Zengy, Z Wang, T Luz, J Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Face super-resolution (SR) algorithms have recently made significant progress. However,
most existing methods prefer to employ texture and structure information together to promote …
most existing methods prefer to employ texture and structure information together to promote …
Mutual Correlation Network for few-shot learning
D Chen, F Chen, D Ouyang, J Shao - Neural Networks, 2024 - Elsevier
Abstract Most metric-based Few-Shot Learning (FSL) methods focus on learning good
embeddings of images. However, these methods either lack the ability to explore the cross …
embeddings of images. However, these methods either lack the ability to explore the cross …
Multi-Scale Feature Fusion and Structure-Preserving Network for Face Super-Resolution
D Yang, Y Wei, C Hu, X Yu, C Sun, S Wu, J Zhang - Applied Sciences, 2023 - mdpi.com
Deep convolutional neural networks have demonstrated significant performance
improvements in face super-resolution tasks. However, many deep learning-based …
improvements in face super-resolution tasks. However, many deep learning-based …
Non-local degradation modeling for spatially adaptive single image super-resolution
Existing methods for single image super-resolution (SISR) model the blur kernel as spatially
invariant across the entire image, and are susceptible to the adverse effects of textureless …
invariant across the entire image, and are susceptible to the adverse effects of textureless …
Omnidirectional image super-resolution via position attention network
For convenient transmission, omnidirectional images (ODIs) usually follow the
equirectangular projection (ERP) format and are low-resolution. To provide better immersive …
equirectangular projection (ERP) format and are low-resolution. To provide better immersive …
Bi-level weighted mixed-domain self-attention network for non-contact heart rate estimation
W Ren, Y Chen, D Zhang, HR Karimi - Knowledge-Based Systems, 2024 - Elsevier
Remote Photoplethysmography (rPPG) technique plays a pivotal role in non-contact heart
rate (HR) estimation. The existing deep learning-based technology has obtained better …
rate (HR) estimation. The existing deep learning-based technology has obtained better …
Enhancing Face Image Quality: Strategic Patch Selection with Deep Reinforcement Learning and Super-Resolution Boost via RRDB
E Altinkaya, B Barakli - IEEE Access, 2024 - ieeexplore.ieee.org
Facial super-resolution (FSR) is a critical research area whose goal is to improve visual
quality by converting low-resolution facial images to high resolution ones. Research in FSR …
quality by converting low-resolution facial images to high resolution ones. Research in FSR …
Structure-Texture Dual Preserving for Remote Sensing Image Super-Resolution
K Zhao, T Lu, Y Zhang, J Jiang… - IEEE Journal of …, 2024 - ieeexplore.ieee.org
Most of the existing remote sensing image super-resolution (SR) methods based on deep
learning tend to learn the mapping from low-resolution (LR) images to high-resolution (HR) …
learning tend to learn the mapping from low-resolution (LR) images to high-resolution (HR) …
Attention-Guided Multi-scale Interaction Network for Face Super-Resolution
Recently, CNN and Transformer hybrid networks demonstrated excellent performance in
face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid …
face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid …