Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but is prone to produce artifacts upon challenging cases in real-world scenarios, since joint participation in t...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2023) vom: 03. Feb.
1. Verfasser: Hou, Hao (VerfasserIn)
Weitere Verfasser: Xu, Jun, Hou, Yingkun, Hu, Xiaotao, Wei, Benzheng, Shen, Dinggang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM355271249
003 DE-627
005 20231226064010.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2023.3240845  |2 doi 
028 5 2 |a pubmed24n1184.xml 
035 |a (DE-627)NLM355271249 
035 |a (NLM)37022430 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Hou, Hao  |e verfasserin  |4 aut 
245 1 0 |a Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution 
264 1 |c 2023 
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 06.04.2023 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but is prone to produce artifacts upon challenging cases in real-world scenarios, since joint participation in the same degradation branch will impact final performance due to huge domain gap between real-world and synthetic LR ones obtained by generators. To better exploit the powerful generative capability of GAN for real-world face SR, in this paper, we establish two independent degradation branches in the forward and backward cycle-consistent reconstruction processes, respectively, while the two processes share the same restoration branch. Our Semi-Cycled Generative Adversarial Networks (SCGAN) is able to alleviate the adverse effects of the domain gap between the real-world LR face images and the synthetic LR ones, and to achieve accurate and robust face SR performance by the shared restoration branch regularized by both the forward and backward cycle-consistent learning processes. Experiments on two synthetic and two real-world datasets demonstrate that, our SCGAN outperforms the state-of-the-art methods on recovering the face structures/details and quantitative metrics for real-world face SR. The code will be publicly released at https://github.com/HaoHou-98/SCGAN 
650 4 |a Journal Article 
700 1 |a Xu, Jun  |e verfasserin  |4 aut 
700 1 |a Hou, Yingkun  |e verfasserin  |4 aut 
700 1 |a Hu, Xiaotao  |e verfasserin  |4 aut 
700 1 |a Wei, Benzheng  |e verfasserin  |4 aut 
700 1 |a Shen, Dinggang  |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 PP(2023) vom: 03. Feb.  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:PP  |g year:2023  |g day:03  |g month:02 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2023.3240845  |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 PP  |j 2023  |b 03  |c 02