Limits on super-resolution and how to break them
Limits on super-resolution and how to break them
复制标题
DOI：
10.1109/cvpr.2000.854852
复制
发表时间：
2000-06
期刊：
影响因子：
--
通讯作者：
Simon Baker;Takeo Kanade
中科院分区：
文献类型：
--
作者：
Simon Baker;Takeo Kanade
我们分析了超分辨率重建的约束条件。特别是，我们得出一系列的结果都表明，作为放大因子的增加，约束提供的有用信息少得多。众所周知，使用平滑先验可能会有所帮助，但是对于足够大的放大因子，任何平滑先验都会导致过度平滑的结果。因此，我们提出了一种算法，该算法可以为特定类别的场景学习基于先验知识的先验知识，使用该算法可以为人脸和文本提供更好的超分辨率结果。
We analyze the super-resolution reconstruction constraints. In particular we derive a sequence of results which all show that the constraints provide far less useful information as the magnification factor increases. It is well established that the use of a smoothness prior may help somewhat, however for large enough magnification factors any smoothness prior leads to overly smooth results. We therefore propose an algorithm that learns recognition-based priors for specific classes of scenes, the use of which gives far better super-resolution results for both faces and text.