.png){kind=icon}
返回
Single-Image super-resolution-When model adaptation matters
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2021.107931.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, impressive advances have been made in single-image super-resolution. Deep learning is behind much of this success. Deep(er) architecture design and external prior modeling are the key ingredients. The internal contents of the low-resolution input image are neglected with deep modeling, despite earlier works that show the power of using such internal priors. In this paper, we propose a variation of deep residual convolutional neural networks, which has been carefully designed for robustness and efficiency in both learning and testing. Moreover, we propose multiple strategies for model adaptation to the internal contents of the low-resolution input image and analyze their strong points and weaknesses. By trading runtime and using internal priors, we achieve improvements from 0.1 to 0.3 dB PSNR over the reported results on standard datasets. Our adaptation especially favors images with repetitive structures or high resolutions. It indicates a more practical usage when our adaption approach applies to sequences or videos in which adjacent frames are strongly correlated in their contents. Moreover, the approach can be combined with other simple techniques, such as back-projection and enhanced prediction, to realize further improvements. (c) 2021 Published by Elsevier Ltd.
Keyword:
Internal prior
Model adaptation
Deep convolutional neural network
Projection skip connection
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Video super-resolution using an adaptive superpixel-guided auto-regressive model.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Convolutional network architectures for super-resolution/sub-pixel mapping of drone-derived imagesPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Brain atlas fusion from high-thickness diagnostic magnetic resonance images by learning-based super-resolution通过基于学习的超分辨率从高厚度诊断磁共振图像融合脑图谱PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Simultaneous color-depth super-resolution with conditional generative adversarial networksPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Locally affine patch mapping and global refinement for image super-resolution图像超分辨率的局部仿射面片映射和全局细化PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Super-resolution of human face image using canonical correlation analysisPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容