Parametric meta-filter modeling from a single example pair

Huang, Shi-Sheng, Zhang, Guo-Xin, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Kopf, Johannes, Cohen-Or, Daniel and Hu, Shi-Min 2014. Parametric meta-filter modeling from a single example pair. The Visual Computer 30 (6-8) , pp. 673-684. 10.1007/s00371-014-0973-y

Preview

PDF - Accepted Post-Print Version Download (3MB) | Preview

Abstract

We present a method for learning a meta- �lter from an example pair comprising an original image A and its �ltered version A0 using an unknown image �lter. A meta-�lter is a parametric model, consisting of a spatially varying linear combination of simple basis �lters. We introduce a technique for learning the parameters of the meta-�lter f such that it approximates the e�ects of the unknown �lter, i.e., f(A) approximates A0. The meta-�lter 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-�lters that approximate a large variety of common image �lters with high accuracy both visually and quantitatively.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Springer
ISSN:	0178-2789
Date of First Compliant Deposit:	30 March 2016
Last Modified:	26 Nov 2024 11:30
URI:	https://orca.cardiff.ac.uk/id/eprint/66233

Citation Data

Cited 9 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item