Conditioned Regression Models for Non-Blind Single Image Super-Resolution
ICCV(2015)
摘要
Single image super-resolution is an important task in the field of computer vision and finds many practical applications. Current state-of-the-art methods typically rely on machine learning algorithms to infer a mapping from low-to high-resolution images. These methods use a single fixed blur kernel during training and, consequently, assume the exact same kernel underlying the image formation process for all test images. However, this setting is not realistic for practical applications, because the blur is typically different for each test image. In this paper, we loosen this restrictive constraint and propose conditioned regression models (including convolutional neural networks and random forests) that can effectively exploit the additional kernel information during both, training and inference. This allows for training a single model, while previous methods need to be re-trained for every blur kernel individually to achieve good results, which we demonstrate in our evaluations. We also empirically show that the proposed conditioned regression models (i) can effectively handle scenarios where the blur kernel is different for each image and (ii) outperform related approaches trained for only a single kernel.
更多查看译文
关键词
conditioned regression models,nonblind single image superresolution,computer vision,machine learning algorithms,high-resolution images,low-resolution images,fixed blur kernel,image formation process,convolutional neural networks,random forests
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络