Adaptive Transform Domain Image Super-resolution Via Orthogonally Regularized Deep Networks.
IEEE Transactions on Image Processing(2019)
摘要
Deep learning methods, in particular, trained convolutional neural networks (CNNs) have recently been shown to produce compelling results for single image super-resolution (SR). Invariably, a CNN is learned to map the low resolution (LR) image to its corresponding high resolution (HR) version in the spatial domain. We propose a novel network structure for learning the SR mapping function in an ima...
更多查看译文
关键词
Discrete cosine transforms,Training,Spatial resolution,Deep learning,Dictionaries
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要