Parametric Meta-Filter Modeling from a Single Example Pair
Shi-Sheng Huang, Guo-Xin Zhang, Yu-Kun Lai, Johannes Kopf, Daniel Cohen-Or, Shi-Min Hu
CGI 2014


We present a method for learning a meta-Filter from an example pair comprising an original image A and its Filtered version A0 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 f such that it approximates the effects of the unknown Filter, i.e., f(A) approximates A0. 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.

Application: Filter Transfer Results

Application: Filter Edit Results


This work was supported by the National Basic Research Project of China (Project Number 2011 CB302205), the Natural Science Foundation of China (Project Number 61120106007, 61133008), the National High Technology Research and Development Program of China (Project Number 2012AA011802) and Tsinghua University Initiative Scientific Research Program.


author = {Shi-Sheng Huang and Guo-Xin Zhang and Yu-Kun Lai and Johannes Kopf and Daniel Cohen-Or and Shi-Min Hu},
title = {Parametric Meta-Filter Modeling from a Single Example Pair},
journal = {The Visual Computer(Special Issue of 31st Computer Graphics International 2014)},
volume = {},
number = {},
year = {2014},
pages = {accepted}

Supplementary Materials:

1. We created a webpage to show many other application results, such as Filter Transfer and Filter Edit, please visit it (here).

2. Or you can download a pdf file to see the results. (SupplementaryMaterials.pdf[11M]).

3. The comparison results with [Zhang et al, TMM 2013] can be downloaded:(Comparison.pdf[5M]).

Source Code:

please email me to get the source code, for Meta Filter Learning, Meta Filter Transfer and Meta Filter Edit. If you use our code, please cite our paper, thanks!

paper [3M] slides [coming soon...]