{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:26:06Z","timestamp":1780057566961,"version":"3.54.0"},"reference-count":188,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991450"],"award-info":[{"award-number":["61991450"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Laboratory of Marine IntelliSense and Computation","award":["ZDSYS20200811142605016"],"award-info":[{"award-number":["ZDSYS20200811142605016"]}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1149783"],"award-info":[{"award-number":["1149783"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,3,1]]},"DOI":"10.1109\/tpami.2022.3181070","type":"journal-article","created":{"date-parts":[[2022,6,9]],"date-time":"2022-06-09T20:33:42Z","timestamp":1654806822000},"page":"3121-3138","source":"Crossref","is-referenced-by-count":336,"title":["GAN Inversion: A Survey"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0087-3525","authenticated-orcid":false,"given":"Weihao","family":"Xia","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2288-5079","authenticated-orcid":false,"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Vision Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6427-1024","authenticated-orcid":false,"given":"Yujiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1174-610X","authenticated-orcid":false,"given":"Jing-Hao","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Statistical Science, University College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California at Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2672","article-title":"Generative adversarial networks","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413868"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.299"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.36"},{"key":"ref11","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras"},{"key":"ref12","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00584"},{"key":"ref17","article-title":"On the \u201dsteerability\u201d of generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jahanian"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00460"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3167305"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00664"},{"key":"ref31","article-title":"Adversarial feature learning","author":"Donahue","year":"2016"},{"key":"ref32","article-title":"Adversarially learned inference","author":"Dumoulin","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01598-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00251"},{"key":"ref36","first-page":"2421","article-title":"Intermediate layer optimization for inverse problems using deep generative models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Daras"},{"key":"ref37","first-page":"5367","article-title":"Prior image-constrained reconstruction using style-based generative models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kelkar"},{"key":"ref38","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.32"},{"key":"ref40","first-page":"487","article-title":"Learning deep features for scene recognition using places database","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref41","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875194"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875194"},{"key":"ref44","first-page":"5767","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Gulrajani"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref46","article-title":"Invertible conditional GANs for image editing","author":"Perarnau"},{"key":"ref47","article-title":"The MNIST database of handwritten digits","author":"LeCun","year":"1998"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"ref49","first-page":"5770","article-title":"Editing in style: Uncovering the local semantics of GANs","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Edo"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01454"},{"key":"ref51","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref53","first-page":"170","article-title":"StyleGAN2 distillation for feed-forward image manipulation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Yuri"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01310-5"},{"key":"ref55","article-title":"Using latent space regression to analyze and leverage compositionality in GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chai"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00441"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01475"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01365"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01368"},{"key":"ref64","article-title":"Improved StyleGAN embedding: Where are the good latents?","author":"Zhu","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01109"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01110"},{"key":"ref70","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Karras"},{"key":"ref71","first-page":"852","article-title":"Alias-free generative adversarial networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karras"},{"key":"ref72","article-title":"Towards the high-quality anime characters generation with generative adversarial networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Jin"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01065"},{"key":"ref74","article-title":"StyleNeRF: A style-based 3D-aware generator for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.121"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24785-9_37"},{"key":"ref81","article-title":"An empirical study on evaluation metrics of generative adversarial networks","author":"Xu","year":"2018"},{"key":"ref82","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref85","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref86","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417826"},{"key":"ref89","article-title":"Unsupervised discovery of interpretable directions in the GAN latent space","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Voynov"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3447648"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_3"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_11"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref94","article-title":"Inverting layers of a large generator","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Bau"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01411"},{"key":"ref97","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/0370-2693(87)91197-X"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00618"},{"key":"ref102","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha"},{"key":"ref103","article-title":"GAN dissection: Visualizing and understanding generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bau"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00480"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897459"},{"key":"ref106","article-title":"InfinityGAN: Towards infinite-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref107","first-page":"13910","article-title":"Inverting deep generative models, one layer at a time","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref109","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. ICML Workshop Deep Learn. Audio, Speech, Lang. Process.","author":"Maas"},{"key":"ref110","first-page":"14707","article-title":"Likelihood ratios for out-of-distribution detection","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref111","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref112","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1038\/mp.2014.1"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.5334\/irsp.179"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01100"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/99"},{"key":"ref118","article-title":"GAN steerability without optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nurit"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00711"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref122","article-title":"Mind the gap: Domain gap control for single shot domain adaptation for generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref123","article-title":"Enjoy your editing: Controllable GANs for image editing via latent space navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhuang"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00367"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459805"},{"key":"ref126","article-title":"Controlling generative models with continuous factors of variations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Plumerault"},{"key":"ref127","article-title":"Unsupervised discovery of disentangled manifolds in GANs","author":"Lu","year":"2020"},{"key":"ref128","first-page":"9841","article-title":"GANSpace: Discovering interpretable GAN controls","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Erik"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00665"},{"key":"ref130","first-page":"16648","article-title":"Low-rank subspaces in GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref132","article-title":"Do 2D GANs know 3D shape? Unsupervised 3D shape reconstruction from 2D image GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pan"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00181"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00445"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01371"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475226"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2021.11.HVEI-112"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1016\/j.zemedi.2020.05.001"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.5220\/0010393900002865"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00202"},{"key":"ref141","article-title":"Few-shot semantic image synthesis using StyleGAN prior","author":"Endo","year":"2021"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01114"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.029"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00126"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392386"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.266"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00228"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref149","first-page":"9446","article-title":"Deep image prior","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Ulyanov"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00467"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref152","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref153","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_16"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00337"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101552"},{"key":"ref157","article-title":"Latent space non-linear statistics","author":"Kuhnel","year":"2018"},{"key":"ref158","article-title":"Do not escape from the manifold: Discovering the local coordinates on the latent space of GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choi"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00924"},{"key":"ref160","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref161","article-title":"LaDDer: Latent data distribution modelling with a generative prior","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Lin"},{"key":"ref162","article-title":"Cooperative semantic segmentation and image restoration in adverse environmental conditions","author":"Xia","year":"2019"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794220"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793573"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01322-1"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3470848"},{"key":"ref169","article-title":"Neural human video rendering by learning dynamic textures and rendering-to-video translation","author":"Liu","year":"2020","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323020"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00008"},{"key":"ref173","first-page":"6767","article-title":"BlockGAN: Learning 3D object-aware scene representations from unlabelled images","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Nguyen-Phuoc"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050505"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_19"},{"key":"ref176","first-page":"9276","article-title":"Geo-PIFu: Geometry and pixel aligned implicit functions for single-view human reconstruction","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"He"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1145\/3395208"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00703"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00729"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392390"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323008"},{"key":"ref183","first-page":"4089","article-title":"Monocular neural image based rendering with continuous view control","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Chen"},{"key":"ref184","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref185","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref186","article-title":"Controllable text-to-image generation","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref187","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10036240\/9792208-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10036240\/09792208.pdf?arnumber=9792208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:26:10Z","timestamp":1743794770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9792208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":188,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3181070","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,1]]}}}