Semi-discrete Optimal Transport in Patch Space for Enriching Gaussian Textures

被引:1
|
作者
Galerne, Bruno [1 ,2 ]
Leclaire, Arthur [3 ]
Rabin, Julien [4 ]
机构
[1] Univ Paris 05, Lab MAP5, Paris, France
[2] CNRS, Sorbonne Paris Cite, Paris, France
[3] Univ Paris Saclay, CNRS, ENS Cachan, CMLA, F-94235 Cachan, France
[4] Normandie Univ, ENSICAEN, CNRS, GREYC, F-14000 Caen, France
来源
关键词
Optimal transport; Texture synthesis; Patch distribution; IMAGE;
D O I
10.1007/978-3-319-68445-1_12
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A bilevel texture model is proposed, based on a local transform of a Gaussian random field. The core of this method relies on the optimal transport of a continuous Gaussian distribution towards the discrete exemplar patch distribution. The synthesis then simply consists in a fast post-processing of a Gaussian texture sample, boiling down to an improved nearest-neighbor patch matching, while offering theoretical guarantees on statistical compliancy.
引用
收藏
页码:100 / 108
页数:9
相关论文
共 50 条