{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:37:29Z","timestamp":1778081849940,"version":"3.51.4"},"reference-count":257,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/jproc.2021.3049196","type":"journal-article","created":{"date-parts":[[2021,2,2]],"date-time":"2021-02-02T04:42:13Z","timestamp":1612240933000},"page":"839-862","source":"Crossref","is-referenced-by-count":178,"title":["Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications"],"prefix":"10.1109","volume":"109","author":[{"ORCID":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/orcid.org\/0000-0002-2951-2398","authenticated-orcid":false,"given":"Ming-Yu","family":"Liu","sequence":"first","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"given":"Xun","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"given":"Jiahui","family":"Yu","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}]},{"given":"Ting-Chun","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/orcid.org\/0000-0002-1348-4740","authenticated-orcid":false,"given":"Arun","family":"Mallya","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]}],"member":"263","reference":[{"key":"ref170","first-page":"382","article-title":"COCO-FUNIT: Few-shot unsupervised image translation with a content conditioned style encoder","author":"saito","year":"2020","journal-title":"Proc ECCV"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.481"},{"key":"ref173","first-page":"5228","article-title":"Assessing generative models via precision and recall","author":"sajjadi","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref176","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref175","first-page":"448","article-title":"Deep Boltzmann machines","author":"salakhutdinov","year":"0","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref178","article-title":"GRAF: Generative radiance fields for 3D-aware image synthesis","author":"schwarz","year":"2020","journal-title":"arXiv 2007 02442"},{"key":"ref177","article-title":"PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications","author":"salimans","year":"2017","journal-title":"Proc ICLR"},{"key":"ref168","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Proc ICML"},{"key":"ref169","first-page":"2018","article-title":"Stabilizing training of generative adversarial networks through regularization","author":"roth","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref39","first-page":"4414","article-title":"Unsupervised learning of disentangled representations from video","author":"denton","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref38","article-title":"Optimal unsupervised domain translation","author":"de b\u00e9zenac","year":"2019","journal-title":"arXiv 1906 01292"},{"key":"ref33","article-title":"Efficient video generation on complex datasets","author":"clark","year":"2019","journal-title":"arXiv 1907 06571"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_11"},{"key":"ref30","first-page":"864","article-title":"PixelSNAIL: An improved autoregressive generative model","author":"chen","year":"2018","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.5.889"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00187"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00862"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref184","first-page":"7137","article-title":"First order motion model for image animation","author":"siarohin","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00249"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00246"},{"key":"ref188","first-page":"3738","article-title":"Ladder variational autoencoders","author":"s\u00f8nderby","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00254"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00333"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00467"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref21","first-page":"334","article-title":"The 2018 PIRM challenge on perceptual image super-resolution","author":"blau","year":"2018","journal-title":"Proc ECCV Workshop"},{"key":"ref24","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"2019","journal-title":"Proc ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"ref50","article-title":"Vid2Game: Controllable characters extracted from real-world videos","author":"gafni","year":"2020","journal-title":"Proc ICLR"},{"key":"ref51","article-title":"The role of minimal complexity functions in unsupervised learning of semantic mappings","author":"galanti","year":"2018","journal-title":"Proc ICLR"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905015"},{"key":"ref153","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"ref150","first-page":"271","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","author":"nowozin","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.580"},{"key":"ref151","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","author":"odena","year":"2017","journal-title":"Proc ICML"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_8"},{"key":"ref147","first-page":"7588","article-title":"HoloGAN: Unsupervised learning of 3d representations from natural images","author":"nguyen-phuoc","year":"2019","journal-title":"Proc CVPR"},{"key":"ref148","article-title":"BlockGAN: Learning 3D object-aware scene representations from unlabelled images","author":"nguyen-phuoc","year":"2020","journal-title":"arXiv 2002 08988"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref59","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref58","article-title":"NIPS 2016 tutorial: Generative adversarial networks","author":"goodfellow","year":"2017","journal-title":"arXiv 1701 00160"},{"key":"ref57","first-page":"1287","article-title":"Image-to-image translation for cross-domain disentanglement","author":"gonzalez-garcia","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00332"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00584"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00888"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275043"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.517"},{"key":"ref40","article-title":"NICE: Non-linear independent components estimation","author":"dinh","year":"2015","journal-title":"Proc ICLR"},{"key":"ref167","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc ICML"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"ref165","article-title":"Seeing is not necessarily believing: Limitations of BigGANs for data augmentation","author":"ravuri","year":"2019","journal-title":"Proc ICLR Workshop"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_41"},{"key":"ref163","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"Proc ICLR"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01013"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00899"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01210-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13632"},{"key":"ref6","first-page":"214","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"Proc ICML"},{"key":"ref5","first-page":"195","article-title":"Augmented CycleGAN: Learning many-to-many mappings from unpaired data","author":"almahairi","year":"2018","journal-title":"Proc ICML"},{"key":"ref8","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130818"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref9","article-title":"Rethinking the truly unsupervised image-to-image translation","author":"baek","year":"2020","journal-title":"arXiv 2006 06500"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00923"},{"key":"ref45","first-page":"3608","article-title":"Implicit generation and generalization in energy-based models","author":"du","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33275-3_2"},{"key":"ref47","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref41","article-title":"Density estimation using real NVP","author":"dinh","year":"2017","journal-title":"Proc ICLR"},{"key":"ref44","first-page":"474","article-title":"Soft-gated warping-GAN for pose-guided person image synthesis","author":"dong","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_2"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref76","article-title":"On the ‘steerability’ of generative adversarial networks","author":"jahanian","year":"2020","journal-title":"Proc ICLR"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref74","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00183"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref60","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6717"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01241"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref64","first-page":"5767","article-title":"Improved training of wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"heusel","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818056"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.486"},{"key":"ref194","article-title":"Edge guided GANs with semantic preserving for semantic image synthesis","author":"tang","year":"2020","journal-title":"arXiv 2003 13898"},{"key":"ref195","first-page":"10521","article-title":"Boundless: Generative adversarial networks for image extension","author":"teterwak","year":"2019","journal-title":"Proc ICCV"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14022"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00854"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref93","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"Proc ICLR"},{"key":"ref191","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc ICML"},{"key":"ref92","first-page":"10215","article-title":"Glow: Generative flow with invertible $1\\times1$\n convolutions","author":"kingma","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref91","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref90","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"kim","year":"2017","journal-title":"Proc ICML"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref99","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"2016","journal-title":"Proc ICML"},{"key":"ref96","first-page":"3581","article-title":"A large-scale study on regularization and normalization in GANs","author":"kurach","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref97","first-page":"3927","article-title":"Improved precision and recall metric for assessing generative models","author":"kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00176"},{"key":"ref81","first-page":"4931","article-title":"On relativistic f-divergences","author":"jolicoeur-martineau","year":"2020","journal-title":"Proc ICML"},{"key":"ref84","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"karras","year":"2018","journal-title":"Proc ICLR"},{"key":"ref83","first-page":"1771","article-title":"Video pixel networks","author":"kalchbrenner","year":"2017","journal-title":"Proc ICML"},{"key":"ref80","article-title":"The relativistic discriminator: A key element missing from standard GAN","author":"jolicoeur-martineau","year":"2019","journal-title":"Proc ICLR"},{"key":"ref89","article-title":"Painting outside as inside: Edge guided image outpainting via bidirectional rearrangement with progressive step learning","author":"kim","year":"2020","journal-title":"arXiv 2010 01810"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref86","first-page":"8110","article-title":"Analyzing and improving the image quality of StyleGAN","author":"karras","year":"2020","journal-title":"Proc CVPR"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201350"},{"key":"ref101","article-title":"A tutorial on energy-based learning","author":"lecun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref100","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073209"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.514"},{"key":"ref204","first-page":"5929","article-title":"Deep generative models for distribution-preserving lossy compression","author":"tschannen","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref201","article-title":"Lecture 6.5—RmsProp: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012","journal-title":"Proc Neural Netw Mach Learn (COURSERA)"},{"key":"ref202","article-title":"Wasserstein auto-encoders","author":"tolstikhin","year":"2018","journal-title":"Proc ICLR"},{"key":"ref207","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"van den oord","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref208","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"Proc ICLR"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref206","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv 1607 08022"},{"key":"ref211","first-page":"1","article-title":"Realistic speech-driven facial animation with GANs","author":"vougioukas","year":"2019","journal-title":"Proc IJCV"},{"key":"ref210","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.361"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00159"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref216","first-page":"8695","article-title":"Few-shot video-to-video synthesis","author":"wang","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref217","first-page":"1152","article-title":"Video-to-video synthesis","author":"wang","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref219","article-title":"One-shot free-view neural talking-head synthesis for video conferencing","author":"wang","year":"2020","journal-title":"arXiv 2011 15126"},{"key":"ref220","first-page":"63","article-title":"ESRGAN: Enhanced super-resolution generative adversarial networks","author":"wang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref222","first-page":"331","article-title":"Image inpainting via generative multi-column convolutional neural networks","author":"wang","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00451"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00599"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_37"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref225","first-page":"7467","article-title":"SynSin: End-to-end view synthesis from a single image","author":"wiles","year":"2020","journal-title":"Proc CVPR"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00606"},{"key":"ref223","article-title":"Generative adversarial networks in computer vision: A survey and taxonomy","author":"wang","year":"2019","journal-title":"arXiv 1906 01529"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.12.009"},{"key":"ref126","first-page":"700","article-title":"Are GANs created equal? A large-scale study","author":"lucic","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref125","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"lotter","year":"2017","journal-title":"Proc ICLR"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01121"},{"key":"ref129","first-page":"406","article-title":"Pose guided person image generation","author":"ma","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref128","article-title":"Exemplar guided unsupervised image-to-image translation with semantic consistency","author":"ma","year":"2019","journal-title":"Proc ICLR"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00018"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00152"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00037"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_22"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2914583"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"ref230","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref231","first-page":"91","article-title":"ESTHER: Extremely simple image translation through self-regularization","author":"yang","year":"2018","journal-title":"Proc BMVC"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref234","first-page":"201","article-title":"Diversity-sensitive conditional generative adversarial networks","author":"yang","year":"2019","journal-title":"Proc ICLR"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref236","article-title":"Wide activation for efficient and accurate image super-resolution","author":"yu","year":"2019","journal-title":"Proc BMVC"},{"key":"ref136","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2016","journal-title":"Proc ICLR"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275099"},{"key":"ref138","first-page":"3693","article-title":"Which training methods for GANs do actually converge?","author":"mescheder","year":"2018","journal-title":"ICML"},{"key":"ref137","first-page":"3693","article-title":"Unsupervised attention-guided image-to-image translation","author":"mejjati","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00704"},{"key":"ref140","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"Proc ICLR"},{"key":"ref141","article-title":"cGANs with projection discriminator","author":"miyato","year":"2018","journal-title":"Proc ICLR"},{"key":"ref142","article-title":"InstaGAN: Instance-aware image-to-image translation","author":"mo","year":"2019","journal-title":"Proc ICLR"},{"key":"ref143","first-page":"7176","article-title":"Reliable fidelity and diversity metrics for generative models","author":"naeem","year":"2020","journal-title":"Proc ICML"},{"key":"ref2","first-page":"8296","article-title":"Image2StyleGAN++: How to edit the embedded images?","author":"abdal","year":"2020","journal-title":"CVPR"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275075"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref145","article-title":"EdgeConnect: Generative image inpainting with adversarial edge learning","author":"nazeri","year":"2019","journal-title":"arXiv 1901 00212"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00158"},{"key":"ref242","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2019","journal-title":"Proc ICML"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00565"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240536"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00262"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00153"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_11"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00381"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00432"},{"key":"ref106","article-title":"Harmonizing maximum likelihood with GANs for multimodal conditional generation","author":"lee","year":"2019","journal-title":"Proc ICLR"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref103","article-title":"Stochastic adversarial video prediction","author":"lee","year":"2018","journal-title":"arXiv 1804 01523"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref112","article-title":"Geometric GAN","author":"hyun lim","year":"2017","journal-title":"arXiv 1705 02894"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref250","article-title":"Example-guided image synthesis across arbitrary scenes using masked spatial-channel attention and self-supervision","author":"zheng","year":"2020","journal-title":"arXiv 2004 10024"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref255","first-page":"465","article-title":"Toward multimodal image-to-image translation","author":"zhu","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00153"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00245"},{"key":"ref256","first-page":"118","article-title":"Visual object networks: Image generation with disentangled 3D representations","author":"zhu","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00870"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref13","article-title":"GAN dissection: Visualizing and understanding generative adversarial networks","author":"bau","year":"2019","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00460"},{"key":"ref15","article-title":"Structural-analogy from a single image pair","author":"benaim","year":"2020","journal-title":"arXiv 2004 02222"},{"key":"ref16","first-page":"752","article-title":"One-sided unsupervised domain mapping","author":"benaim","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01065"},{"key":"ref17","first-page":"2104","article-title":"One-shot unsupervised cross domain translation","author":"benaim","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref117","article-title":"Unsupervised image-to-image translation networks","author":"liu","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref19","article-title":"Demystifying MMD GANs","author":"bi?kowski","year":"2018","journal-title":"Proc ICLR"},{"key":"ref119","first-page":"469","article-title":"Coupled generative adversarial networks","author":"liu","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_2"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3333002"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2996594"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01055"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref122","first-page":"570","article-title":"Learning to predict layout-to-image conditional convolutions for semantic image synthesis","author":"liu","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/5\/9420072\/09343694.pdf?arnumber=9343694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T01:33:10Z","timestamp":1733880790000},"score":1,"resource":{"primary":{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/9343694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":257,"journal-issue":{"issue":"5"},"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1109\/jproc.2021.3049196","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}