Non-linear convolution based controllable image analogies and self analogies

Residential College	false
Status	已發表Published
	Non-linear convolution based controllable image analogies and self analogies
	Gu Y.2; Wu E.2
	2008-03-01
Source Publication	Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics
ISSN	10039775
Volume	20 Issue:3 Pages:332-336
Abstract	This paper presents a novel method of image analogies, to promote the learning from image style. By a definition of style as a non-linear convolution, the style of the image may be studied by kernel estimation, and style transfer could be conducted by executing the learned convolution. Furthermore, we may repeatedly apply a stylization process on an image to generate an analogized image series, in help to realize controllable image analogies. In addition, we can also extend this idea to self analogies, applied to enhance the sharpness of images.
Keyword	Controllable analogies Image analogies Non-linear convolution Style learning
URL	View the original
Language	英語English
Fulltext Access	View Full-Text via Scopus
Document Type	Journal article
Collection	University of Macau
Affiliation	1.Faculty of Science and Technology 2.Institute of Software Chinese Academy of Sciences
Recommended Citation GB/T 7714	Gu Y.,Wu E.. Non-linear convolution based controllable image analogies and self analogies[J]. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2008, 20(3), 332-336.
APA	Gu Y.., & Wu E. (2008). Non-linear convolution based controllable image analogies and self analogies. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 20(3), 332-336.
MLA	Gu Y.,et al."Non-linear convolution based controllable image analogies and self analogies".Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 20.3(2008):332-336.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh