We present a method for learning a meta-filter from an example pair comprising an original image A and its filtered version A′ 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 A ′. 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.
- Filter space
- Image filters
- Learning and Transfer
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Computer Graphics and Computer-Aided Design