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
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]).