期刊
JOURNAL OF MATHEMATICAL IMAGING AND VISION
卷 62, 期 3, 页码 456-470出版社
SPRINGER
DOI: 10.1007/s10851-019-00923-x
关键词
Inverse problems; Deep learning; Regularization by architecture; Deep inverse prior; Deep image prior
类别
资金
- Deutsche Forschungsgemeinschaft (DFG) [GRK 2224/1]
- Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) [276397488-SFB 1232]
- European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie Grant [765374]
The present paper studies so-called deep image prior (DIP) techniques in the context of ill-posed inverse problems. DIP networks have been recently introduced for applications in image processing; also first experimental results for applying DIP to inverse problems have been reported. This paper aims at discussing different interpretations of DIP and to obtain analytic results for specific network designs and linear operators. The main contribution is to introduce the idea of viewing these approaches as the optimization of Tikhonov functionals rather than optimizing networks. Besides theoretical results, we present numerical verifications.
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