中科院自动化所联合北方电子设备研究所提多输入文本人脸合成方法( 二 )


参考文献:
1.OsaidRehmanNasir,ShaileshKumarJha,ManrajSinghGrover,YiYu,AjitKumar,andRajivRatnShah.2019.Text2FaceGAN:facegenerationfromfinegrainedtextualdescriptions.InIEEEInternationalConferenceonMultimediaBigData(BigMM).58–67.
2.XiangChen,LingboQing,XiaohaiHe,XiaodongLuo,andYiningXu.2019.FTGAN:Afully-trainedgenerativeadversarialnetworksfortexttofacegeneration.arXivpreprintarXiv:1904.05729(2019).
3.DavidStap,MauritsBleeker,SarahIbrahimi,andMaartjeterHoeve.2020.Conditionalimagegenerationandmanipulationforuser-specifiedcontent.arXivpreprintarXiv:2005.04909(2020).
4.WeihaoXia,YujiuYang,Jing-HaoXue,andBaoyuanWu.2021.TediGAN:Textguideddiverseimagegenerationandmanipulation.InProceedingsoftheIEEEConferenceonComputerVisionandPatternRecognition(CVPR).2256–2265.
5.TaoXu,PengchuanZhang,QiuyuanHuang,HanZhang,ZheGan,XiaoleiHuang,andXiaodongHe.2018.Attngan:Fine-grainedtexttoimagegenerationwithattentionalgenerativeadversarialnetworks.InProceedingsoftheIEEEConferenceonComputerVisionandPatternRecognition(CVPR).1316–1324.
6.BowenLi,XiaojuanQi,ThomasLukasiewicz,andPhilipTorr.2019.Controllabletext-to-imagegeneration.InAdvancesinNeuralInformationProcessingSystems(NeuIPS).2065–2075.