.png){kind=icon}
返回
Parametric meta-filter modeling from a single example pair
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-014-0973-y.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present a method for learning a meta-filter from an example pair comprising an original image and its filtered version using an unknown image filter. A meta-filter is a parametric model, consisting of a spatially varying linear combination of simple basis filters. We introduce a technique for learning the parameters of the meta-filter such that it approximates the effects of the unknown filter, i.e., approximates . The meta-filter can be transferred to novel input images, and its parametric representation enables intuitive tuning of its parameters to achieve controlled variations. We show that our technique successfully learns and models meta-filters that approximate a large variety of common image filters with high accuracy both visually and quantitatively.
Keyword:
Image filters
Filter space
Sparsity
Learning and Transfer
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
.png){kind=icon}
分享收藏The influence of carrier level and frequency on modulation and beat-detection thresholds for sinusoidal carriers载波电平和频率对正弦载波调制和拍频检测阈值的影响
PREAI
分享收藏
The pathogenicity in mice of respiratory, abortion and paresis isolates of equine herpesvirus-1
PREAI
分享收藏
查看更多内容