|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM317535943 |
| 003 |
DE-627 |
| 005 |
20231225163454.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2021 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2020.3036754
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1058.xml
|
| 035 |
|
|
|a (DE-627)NLM317535943
|
| 035 |
|
|
|a (NLM)33186111
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li, Ru
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a SDP-GAN
|b Saliency Detail Preservation Generative Adversarial Networks for High Perceptual Quality Style Transfer
|
| 264 |
|
1 |
|c 2021
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 24.11.2020
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a The paper proposes a solution to effectively handle salient regions for style transfer between unpaired datasets. Recently, Generative Adversarial Networks (GAN) have demonstrated their potentials of translating images from source domain X to target domain Y in the absence of paired examples. However, such a translation cannot guarantee to generate high perceptual quality results. Existing style transfer methods work well with relatively uniform content, they often fail to capture geometric or structural patterns that always belong to salient regions. Detail losses in structured regions and undesired artifacts in smooth regions are unavoidable even if each individual region is correctly transferred into the target style. In this paper, we propose SDP-GAN, a GAN-based network for solving such problems while generating enjoyable style transfer results. We introduce a saliency network, which is trained with the generator simultaneously. The saliency network has two functions: (1) providing constraints for content loss to increase punishment for salient regions, and (2) supplying saliency features to generator to produce coherent results. Moreover, two novel losses are proposed to optimize the generator and saliency networks. The proposed method preserves the details on important salient regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against several leading prior methods demonstrates the superiority of our method
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Wu, Chi-Hao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Shuaicheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Jue
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Guangfu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Guanghui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zeng, Bing
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 30(2021) vom: 13., Seite 374-385
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:30
|g year:2021
|g day:13
|g pages:374-385
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2020.3036754
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 30
|j 2021
|b 13
|h 374-385
|