期刊
SCALE SPACE AND VARIATIONAL METHODS IN COMPUTER VISION, SSVM 2017
卷 10302, 期 -, 页码 41-53出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-58771-4_4
关键词
Nonlinear spectral decomposition; Total variation regularization; Image fusion; Image composition; Multiscale methods
资金
- EPSRC [EP/M00483X/1, EP/N014588/1]
- Leverhulme Trust
- Newton Trust
- German Research Foundation (DFG) [GRK 1564]
- Israel Science Foundation [718/15]
- ERC via Grant EU FP 7 - ERC Consolidator Grant [615216]
- Cantab Capital Institute for the Mathematics of Information
- CHiPS (Horizon RISE project grant)
- ERC Consolidator Grant 3D Reloaded
- EPSRC [EP/M00483X/1, EP/N014588/1] Funding Source: UKRI
- European Research Council (ERC) [615216] Funding Source: European Research Council (ERC)
In this paper we demonstrate that the framework of non-linear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks. The well-localized and edge-preserving spectral TV decomposition allows to select frequencies of a certain image to transfer particular features, such as wrinkles in a face, from one image to another. We illustrate the effectiveness of the proposed approach in several numerical experiments, including a comparison to the competing techniques of Poisson image editing, linear osmosis, wavelet fusion and Laplacian pyramid fusion. We conclude that the proposed spectral TV image decomposition framework is a valuable tool for semi-and fully-automatic image editing and fusion.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据