{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:45:55Z","timestamp":1762368355943,"version":"build-2065373602"},"reference-count":155,"publisher":"Tsinghua University Press","issue":"1","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T00:00:00Z","timestamp":1635292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s41095-021-0234-8","type":"journal-article","created":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T12:03:16Z","timestamp":1635336196000},"page":"3-31","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Deep image synthesis from intuitive user input: A review and perspectives"],"prefix":"10.26599","volume":"8","author":[{"given":"Yuan","family":"Xue","sequence":"first","affiliation":[{"name":"College of Information Sciences and Technology, the Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Chen","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Brain, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Xu","sequence":"additional","affiliation":[{"name":"Facebook, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song-Hai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolei","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Sciences and Technology, the Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"234_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, H.; Xu, T.; Li, H. S.; Zhang, S. T.; Wang, X. G.; Huang, X. L.; Metaxas, D. StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, 5908\u20135916, 2017.","DOI":"10.1109\/ICCV.2017.629"},{"key":"234_CR2","doi-asserted-by":"crossref","unstructured":"Qiao, T. T.; Zhang, J.; Xu, D. Q.; Tao, D. C. MirrorGAN: Learning text-to-image generation by redescription. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1505\u20131514, 2019.","DOI":"10.1109\/CVPR.2019.00160"},{"key":"234_CR3","doi-asserted-by":"crossref","unstructured":"Zhu, M. F.; Pan, P. B.; Chen, W.; Yang, Y. DM-GAN: Dynamic memory generative adversarial networks for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5795\u20135803, 2019.","DOI":"10.1109\/CVPR.2019.00595"},{"key":"234_CR4","unstructured":"Zhang, H.; Koh, J. Y.; Baldridge, J.; Lee, H.; Yang, Y. F. Cross-modal contrastive learning for text-to-image generation. arXiv preprint arXiv:2101.04702, 2021."},{"key":"234_CR5","doi-asserted-by":"crossref","unstructured":"Karras, T.; Laine, S.; Aila, T. M. A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4396\u20134405, 2019.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"234_CR6","doi-asserted-by":"crossref","unstructured":"Sangkloy, P.; Lu, J. W.; Fang, C.; Yu, F.; Hays, J. Scribbler: Controlling deep image synthesis with sketch and color. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6836\u20136845, 2017.","DOI":"10.1109\/CVPR.2017.723"},{"key":"234_CR7","doi-asserted-by":"crossref","unstructured":"Ghosh, A.; Zhang, R.; Dokania, P.; Wang, O.; Efros, A.; Torr, P.; Shechtman, E. Interactive sketch & fill: Multiclass sketch-to-image translation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 1171\u20131180, 2019.","DOI":"10.1109\/ICCV.2019.00126"},{"key":"234_CR8","doi-asserted-by":"crossref","unstructured":"Gao, C. Y.; Liu, Q.; Xu, Q.; Wang, L. M.; Liu, J. Z.; Zou, C. Q. SketchyCOCO: Image generation from freehand scene sketches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5173\u20135182, 2020.","DOI":"10.1109\/CVPR42600.2020.00522"},{"key":"234_CR9","unstructured":"Liu, R.; Yu, Q.; Yu, S. Unsupervised sketch-to-photo synthesis. arXiv preprint arXiv:1909.08313, 2019."},{"key":"234_CR10","unstructured":"Li, J. N.; Yang, J. M.; Hertzmann, A.; Zhang, J. M.; Xu, T. F. LayoutGAN: Generating graphic layouts with wireframe discriminators arXiv preprint arXiv:1901.06767, 2019."},{"key":"234_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/978-3-030-58574-7_17","volume-title":"Computer Vision \u2014 ECCV 2020","author":"Y Xue","year":"2020","unstructured":"Xue, Y.; Zhou, Z. H.; Huang, X. L. Neural wireframe renderer: Learning wireframe to image translations. In: Computer Vision \u2014 ECCV 2020. Lecture Notes in Computer Science, Vol. 12371. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 279\u2013295, 2020."},{"issue":"1","key":"234_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s41095-020-0162-z","volume":"6","author":"M Wang","year":"2020","unstructured":"Wang, M.; Lyu, X. Q.; Li, Y. J.; Zhang, F. L. VR content creation and exploration with deep learning: A survey. Computational Visual Media Vol. 6, No. 1, 3\u201328, 2020.","journal-title":"Computational Visual Media"},{"key":"234_CR13","unstructured":"Kipf, T. N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016."},{"key":"234_CR14","unstructured":"Salimans, T.; Goodfellow, I.; Zaremba, W.; Cheung, V.; Radford, A.; Chen, X. Improved techniques for training GANs. In: Proceedings of the 29th International Conference on Neural Information Processing Systems, 2234\u20132242, 2016."},{"key":"234_CR15","doi-asserted-by":"crossref","unstructured":"Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818\u20132826, 2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"234_CR16","unstructured":"Heusel, M.; Ramsauer, H.; Unterthiner, T.; Nessler, B.; Hochreiter, S. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 6629\u20136640, 2017."},{"issue":"4","key":"234_CR17","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z.; Bovik, A. C.; Sheikh, H. R.; Simoncelli, E. P. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing Vol. 13, No. 4, 600\u2013612, 2004.","journal-title":"IEEE Transactions on Image Processing"},{"key":"234_CR18","unstructured":"Wang, Z.; Simoncelli, E. P.; Bovik, A. C. Multiscale structural similarity for image quality assessment. In: Proceedings of the 37th Asilomar Conference on Signals, Systems & Computers, 1398\u20131402, 2003."},{"key":"234_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, R.; Isola, P.; Efros, A. A.; Shechtman, E.; Wang, O. The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 586\u2013595, 2018.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"234_CR20","unstructured":"Rezende, D. J.; Mohamed, S. Variational inference with normalizing flows. In: Proceedings of the International Conference on Machine Learning, 1530\u20131538, 2015."},{"key":"234_CR21","unstructured":"Kingma, D. P.; Dhariwal, P. Glow: Generative flow with invertible 1\u00d71 convolutions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 10215\u201310224, 2018."},{"key":"234_CR22","unstructured":"Oord, A. V. D.; Kalchbrenner, N.; Kavukcuoglu, K. Pixel recurrent neural networks. In: Proceedings of the International Conference on Machine Learning, 1747\u20131756, 2016."},{"key":"234_CR23","unstructured":"Oord, A. V. D.; Kalchbrenner, N.; Espeholt, L.; Kavukcuoglu, K.; Vinyals, O.; Graves, A. Conditional image generation with pixelCNN decoders. In: Proceedings of the 29th International Conference on Neural Information Processing Systems, 4790\u20134798, 2016."},{"key":"234_CR24","unstructured":"Salimans, T.; Karpathy, A.; Chen, X.; Kingma, D. P. PixelCNN++: Improving the pixelCNN with discretized logistic mixture likelihood and other modifications. arXiv preprint arXiv:1701.05517, 2017."},{"key":"234_CR25","doi-asserted-by":"crossref","unstructured":"Xu, T.; Zhang, P. C.; Huang, Q. Y.; Zhang, H.; Gan, Z.; Huang, X. L.; He, X. D. AttnGAN: Finegrained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1316\u20131324, 2018.","DOI":"10.1109\/CVPR.2018.00143"},{"key":"234_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-01270-0_13","volume-title":"Computer Vision \u2014 ECCV 2018","author":"Y Y Lu","year":"2018","unstructured":"Lu, Y. Y.; Wu, S. Z.; Tai, Y. W.; Tang, C. K. Image generation from sketch constraint using contextual GAN. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11220. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 213\u2013228, 2018."},{"key":"234_CR27","unstructured":"Ma, L.; Jia, X.; Sun, Q.; Schiele, B.; Tuytelaars, T.; Van Gool, L. Pose guided person image generation. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, 406\u2013416, 2017."},{"key":"234_CR28","doi-asserted-by":"crossref","unstructured":"Ma, L. Q.; Sun, Q. R.; Georgoulis, S.; Van Gool, L.; Schiele, B.; Fritz, M. Disentangled person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 99\u2013108, 2018.","DOI":"10.1109\/CVPR.2018.00018"},{"key":"234_CR29","doi-asserted-by":"crossref","unstructured":"Siarohin, A.; Sangineto, E.; Lathuili\u00e8re, S.; Sebe, N. Deformable GANs for pose-based human image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3408\u20133416, 2018.","DOI":"10.1109\/CVPR.2018.00359"},{"key":"234_CR30","doi-asserted-by":"crossref","unstructured":"Song, S. J.; Zhang, W.; Liu, J. Y.; Mei, T. Unsupervised person image generation with semantic parsing transformation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2352\u20132361, 2019.","DOI":"10.1109\/CVPR.2019.00246"},{"key":"234_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, Z.; Huang, T. T.; Shi, B. G.; Yu, M.; Wang, B. F.; Bai, X. Progressive pose attention transfer for person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2342\u20132351, 2019.","DOI":"10.1109\/CVPR.2019.00245"},{"key":"234_CR32","unstructured":"Belongie, S.; Malik, J.; Puzicha, J. Shape context: A new descriptor for shape matching and object recognition. In: Proceedings of the International Conference on Neural Information Processing Systems, 831\u2013837, 2000."},{"key":"234_CR33","doi-asserted-by":"crossref","unstructured":"Chen, T.; Cheng, M. M.; Tan, P.; Shamir, A.; Hu, S. M. Sketch2Photo: Internet image montage. ACM Transactions on Graphics Vol. 28, No. 5, Article No. 124, 2009.","DOI":"10.1145\/1618452.1618470"},{"key":"234_CR34","unstructured":"Goodfellow, I. J.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio Y. Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, 2672\u20132680, 2014."},{"key":"234_CR35","unstructured":"Mirza, M.; Osindero, S. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014."},{"key":"234_CR36","unstructured":"Miyato, T.; Koyama, M. cGANs with projection discriminator. In: Proceedings of the International Conference on Learning Representations, 2018."},{"key":"234_CR37","unstructured":"Odena, A.; Olah, C.; Shlens, J. Conditional image synthesis with auxiliary classifier GANs. In: Proceedings of the International Conference on Machine Learning, 2642\u20132651, 2017."},{"key":"234_CR38","unstructured":"Kingma, D. P.; Welling, M. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013."},{"key":"234_CR39","unstructured":"Sohn, K.; Lee, H.; Yan, X. Learning structured output representation using deep conditional generative models. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, 3483\u20133491, 2015."},{"key":"234_CR40","unstructured":"Klys, J.; Snell, J.; Zemel, R. Learning latent subspaces in variational autoencoders. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 6444\u20136454, 2018."},{"key":"234_CR41","unstructured":"Ivanov, O.; Figurnov, M.; Vetrov, D. Variational autoencoder with arbitrary conditioning. In: Proceedings of the International Conference on Learning Representations, 2018."},{"key":"234_CR42","unstructured":"Larsen, A. B. L.; S\u00f8nderby, S. K.; Larochelle, H.; Winther, O. Auto encoding beyond pixels using a learned similarity metric. In: Proceedings of the International Conference on Machine Learning, 1558\u20131566, 2016."},{"key":"234_CR43","doi-asserted-by":"crossref","unstructured":"Bao, J. M.; Chen, D.; Wen, F.; Li, H. Q.; Hua, G. C. VAE-GAN: Fine-grained image generation through asymmetric training. In: Proceedings of the IEEE International Conference on Computer Vision, 2764\u20132773, 2017.","DOI":"10.1109\/ICCV.2017.299"},{"key":"234_CR44","doi-asserted-by":"crossref","unstructured":"Nilsback, M. E.; Zisserman, A. Automated flower classification over a large number of classes. In: Proceedings of the 6th Indian Conference on Computer Vision, Graphics & Image Processing, 722\u2013729, 2008.","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"234_CR45","unstructured":"Welinder, P.; Branson, S.; Mita, T.; Wah, C.; Schrofi, F.; Belongie, S.; Perona, P. Caltech-UCSD Birds200. Technical Report CNS-TR-2010-001. California Institute of Technology, 2010."},{"key":"234_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision-ECCV 2014","author":"T Y Lin","year":"2014","unstructured":"Lin, T. Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollfiar, P.; Zitnick, C. L. Microsoft COCO: Common objects in context. In: Computer Vision-ECCV 2014. Lecture Notes in Computer Science, Vol. 8693. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer Cham, 740\u2013755, 2014."},{"key":"234_CR47","unstructured":"Reed, S.; Akata, Z.; Yan, X.; Logeswaran, L.; Schiele, B.; Lee, H. Generative adversarial text to image synthesis. In: Proceedings of the International Conference on Machine Learning, 1060\u20131069, 2016."},{"key":"234_CR48","unstructured":"Radford, A.; Metz, L.; Chintala, S. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015."},{"key":"234_CR49","unstructured":"Mansimov, E.; Parisotto, E.; LeiBa, J.; Salakhutdinov, R. Generating images from captions with attention. arXiv preprint arXiv:1511.02793, 2015."},{"issue":"8","key":"234_CR50","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2019","unstructured":"Zhang, H.; Xu, T.; Li, H. S.; Zhang, S. T.; Wang, X. G.; Huang, X. L.; Metaxas, D. N. StackGAN++: Realistic image synthesis with stacked generative adversarial networks. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 41, No. 8, 1947\u20131962, 2019.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"234_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Z. Z.; Xie, Y. P.; Yang, L. Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6199\u20136208, 2018.","DOI":"10.1109\/CVPR.2018.00649"},{"key":"234_CR52","doi-asserted-by":"crossref","unstructured":"Isola, P.; Zhu, J. Y.; Zhou, T. H.; Efros, A. A. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5967\u20135976, 2017.","DOI":"10.1109\/CVPR.2017.632"},{"key":"234_CR53","doi-asserted-by":"crossref","unstructured":"Yin, G. J.; Liu, B.; Sheng, L.; Yu, N. H.; Wang, X. G.; Shao, J. Semantics disentangling for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2322\u20132331, 2019.","DOI":"10.1109\/CVPR.2019.00243"},{"key":"234_CR54","unstructured":"Reed, S. E.; Akata, Z.; Mohan, S.; Tenka, S.; Schiele, B.; Lee, H. Learning what and where to draw. In: Proceedings of the 29th International Conference on Neural Information Processing Systems, 217\u2013225, 2016."},{"key":"234_CR55","doi-asserted-by":"crossref","unstructured":"Hong, S.; Yang, D. D.; Choi, J.; Lee, H. Inferring semantic layout for hierarchical text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 7986\u20137994, 2018.","DOI":"10.1109\/CVPR.2018.00833"},{"key":"234_CR56","doi-asserted-by":"crossref","unstructured":"Chen, Q. F.; Koltun, V. Photographic image synthesis with cascaded refinement networks. In: Proceedings of the IEEE International Conference on Computer Vision, 1520\u20131529, 2017.","DOI":"10.1109\/ICCV.2017.168"},{"key":"234_CR57","doi-asserted-by":"crossref","unstructured":"Li, W. B.; Zhang, P. C.; Zhang, L.; Huang, Q. Y.; He, X. D.; Lyu, S. W.; Gao, J. F. Object-driven text-to-image synthesis via adversarial training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12166\u201312174, 2019.","DOI":"10.1109\/CVPR.2019.01245"},{"key":"234_CR58","doi-asserted-by":"crossref","unstructured":"Girshick, R. Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, 1440\u20131448, 2015.","DOI":"10.1109\/ICCV.2015.169"},{"key":"234_CR59","doi-asserted-by":"crossref","unstructured":"Johnson, J.; Gupta, A.; Li, F. F. Image generation from scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1219\u20131228, 2018.","DOI":"10.1109\/CVPR.2018.00133"},{"issue":"1","key":"234_CR60","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R.; Zhu, Y. K.; Groth, O.; Johnson, J.; Hata, K. J.; Kravitz, J.; Chen, S.; Kalantidis, Y.; Li, L.-J.; Shamma, D. A. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision Vol. 123, No. 1, 32\u201373, 2017.","journal-title":"International Journal of Computer Vision"},{"key":"234_CR61","doi-asserted-by":"crossref","unstructured":"Caesar, H.; Uijlings, J.; Ferrari, V. COCO-stuff: Thing and stuff classes in context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1209\u20131218, 2018.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"234_CR62","unstructured":"Hinz, T.; Heinrich, S.; Wermter, S. Generating multiple objects at spatially distinct locations. arXiv preprint arXiv:1901.00686, 2019."},{"key":"234_CR63","doi-asserted-by":"crossref","unstructured":"Tan, F. W.; Feng, S.; Ordonez, V. Text2Scene: Generating compositional scenes from textual descriptions. arXiv preprint arXiv:1809.01110, 2018.","DOI":"10.1109\/CVPR.2019.00687"},{"key":"234_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-030-01228-1_41","volume-title":"Computer Vision-ECCV 2018","author":"N Bodla","year":"2018","unstructured":"Bodla, N.; Hua, G.; Chellappa, R. Semi-supervised FusedGAN for conditional image generation. In: Computer Vision-ECCV 2018. Lecture Notes in Computer Science, Vol. 11209. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 689\u2013704, 2018."},{"key":"234_CR65","doi-asserted-by":"crossref","unstructured":"Hinz, T.; Heinrich, S.; Wermter, S. Semantic object accuracy for generative text-to-image synthesis. arXiv preprint arXiv:1910.13321, 2019.","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"234_CR66","doi-asserted-by":"crossref","unstructured":"Wang, T. C.; Liu, M. Y.; Zhu, J. Y.; Tao, A.; Kautz, J.; Catanzaro, B. High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8798\u20138807, 2018.","DOI":"10.1109\/CVPR.2018.00917"},{"issue":"6","key":"234_CR67","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MCG.2011.67","volume":"31","author":"M Eitz","year":"2011","unstructured":"Eitz, M.; Richter, R.; Hildebrand, K.; Boubekeur, T.; Alexa, M. Photosketcher: Interactive sketch-based image synthesis. IEEE Computer Graphics and Applications Vol. 31, No. 6, 56\u201366, 2011.","journal-title":"IEEE Computer Graphics and Applications"},{"key":"234_CR68","doi-asserted-by":"crossref","unstructured":"Hu, S.-M.; Zhang, F.-L.; Wang, M.; Martin, R. R.; Wang, J. PatchNet: A patch-based image representation for interactive library-driven image editing. ACM Transactions on Graphics Vol. 32, No. 6, Article No. 196, 2013.","DOI":"10.1145\/2508363.2508381"},{"key":"234_CR69","doi-asserted-by":"publisher","first-page":"3765","DOI":"10.1109\/ACCESS.2018.2796638","volume":"6","author":"J Y Wang","year":"2018","unstructured":"Wang, J. Y.; Zhao, Y.; Qi, Q.; Huo, Q. M.; Zou, J.; Ge, C.; Liao, J. MindCamera: Interactive sketch-based image retrieval and synthesis. IEEE Access Vol. 6, 3765\u20133773, 2018.","journal-title":"IEEE Access"},{"issue":"8","key":"234_CR70","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1111\/cgf.12665","volume":"34","author":"D Turmukhambetov","year":"2015","unstructured":"Turmukhambetov, D.; Campbell, N. D. F.; Goldman, D. B.; Kautz, J. Interactive sketch-driven image synthesis. Computer Graphics Forum Vol. 34, No. 8, 130\u2013142, 2015.","journal-title":"Computer Graphics Forum"},{"key":"234_CR71","doi-asserted-by":"crossref","unstructured":"Xie, S. N.; Tu, Z. W. Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, 1395\u20131403, 2015.","DOI":"10.1109\/ICCV.2015.164"},{"issue":"6","key":"234_CR72","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1016\/j.cag.2012.03.004","volume":"36","author":"H Winnem\u00f6ller","year":"2012","unstructured":"Winnem\u00f6ller, H.; Kyprianidis, J. E.; Olsen, S. C. XDoG: An eXtended difference-of-Gaussians compendium including advanced image stylization. Computers & Graphics Vol. 36, No. 6, 740\u2013753, 2012.","journal-title":"Computers & Graphics"},{"key":"234_CR73","doi-asserted-by":"crossref","unstructured":"Kang, H.; Lee, S.; Chui, C. K. Coherent line drawing. In: Proceedings of the 5th International Symposium on Non-photorealistic Animation and Rendering, 43\u201350, 2007.","DOI":"10.1145\/1274871.1274878"},{"key":"234_CR74","doi-asserted-by":"crossref","unstructured":"Li, Y. J.; Fang, C.; Hertzmann, A.; Shechtman, E.; Yang, M. H. Im2Pencil: Controllable pencil illustration from photographs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1525\u20131534, 2019.","DOI":"10.1109\/CVPR.2019.00162"},{"key":"234_CR75","doi-asserted-by":"crossref","unstructured":"Li, M. T.; Lin, Z.; Mech, R.; Yumer, E.; Ramanan, D. Photo-sketching: Inferring contour drawings from images. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1403\u20131412, 2019.","DOI":"10.1109\/WACV.2019.00154"},{"key":"234_CR76","doi-asserted-by":"crossref","unstructured":"Gastal, E. S. L.; Oliveira, M. M. Domain transform for edge-aware image and video processing. ACM Transactions on Graphics Vol. 30, No. 4, Article No. 69, 2011.","DOI":"10.1145\/2010324.1964964"},{"issue":"4","key":"234_CR77","doi-asserted-by":"publisher","first-page":"2104","DOI":"10.1121\/1.4899570","volume":"136","author":"G V Hahn-Powell","year":"2014","unstructured":"Hahn-Powell, G. V.; Archangeli, D. AutoTrace: An automatic system for tracing tongue contours. The Journal of the Acoustical Society of America Vol. 136, No. 4, 2104, 2014.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"234_CR78","doi-asserted-by":"crossref","unstructured":"Simo-Serra, E.; Iizuka, S.; Sasaki, K.; Ishikawa, H. Learning to simplify. ACM Transactions on Graphics Vol. 35, No. 4, Article No. 121, 2016.","DOI":"10.1145\/2897824.2925972"},{"key":"234_CR79","doi-asserted-by":"crossref","unstructured":"Chen, W. L.; Hays, J. SketchyGAN: Towards diverse and realistic sketch to image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9416\u20139425, 2018.","DOI":"10.1109\/CVPR.2018.00981"},{"key":"234_CR80","doi-asserted-by":"crossref","unstructured":"Li, Y. H.; Chen, X. J.; Wu, F.; Zha, Z. J. LinesToFacePhoto: Face photo generation from lines with conditional self-attention generative adversarial networks. In: Proceedings of the 27th ACM International Conference on Multimedia, 2323\u20132331, 2019.","DOI":"10.1145\/3343031.3350854"},{"key":"234_CR81","doi-asserted-by":"crossref","unstructured":"G\u00fc\u00e7l\u00fct\u00fcrk, Y.; G\u00fc\u00e7l\u00fc, U.; van Lier, R.; van Gerven, M. A. J. Convolutional sketch inversion. In: Computer Vision-ECCV 2016 Workshops. Lecture Notes in Computer Science, Vol. 9913. Hua, G.; J\u00e9gou, H. Eds. Springer Cham, 810\u2013824, 2016.","DOI":"10.1007\/978-3-319-46604-0_56"},{"key":"234_CR82","unstructured":"Mescheder, L.; Geiger, A.; Nowozin, S. Which training methods for GANs do actually converge? arXiv preprint arXiv:1801.04406, 2018."},{"key":"234_CR83","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision-ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X.; Liu, M. Y.; Belongie, S.; Kautz, J. Multimodal unsupervised image-to-image translation. In: Computer Vision-ECCV 2018. Lecture Notes in Computer Science, Vol. 11207. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 179\u2013196, 2018."},{"key":"234_CR84","doi-asserted-by":"crossref","unstructured":"Portenier, T.; Hu, Q.; Szab\u00f3, A.; Bigdeli, S. A.; Favaro, P.; Zwicker, M. Faceshop: Deep sketch-based face image editing. arXiv preprint arXiv:1804.08972, 2018.","DOI":"10.1145\/3197517.3201393"},{"key":"234_CR85","unstructured":"Xia, W.; Yang, Y.; Xue, J.-H. Calisketch: Stroke calibration and completion for high quality face image generation from poorly-drawn sketches. arXiv preprint arXiv:1911.00426, 2019."},{"key":"234_CR86","doi-asserted-by":"crossref","unstructured":"Chen, S.-Y.; Su, W.; Gao, L.; Xia, S.; Fu, H. DeepFaceDrawing: Deep generation of face images from sketches. ACM Transactions on Graphics Vol. 39, No. 4, Article No. 72, 2020.","DOI":"10.1145\/3386569.3392386"},{"key":"234_CR87","doi-asserted-by":"crossref","unstructured":"Sangkloy, P.; Burnell, N.; Ham, C.; Hays, J. The sketchy database. ACM Transactions on Graphics Vol. 35, No. 4, Article No. 119, 2016.","DOI":"10.1145\/2897824.2925954"},{"key":"234_CR88","doi-asserted-by":"crossref","unstructured":"Eitz, M.; Hays, J.; Alexa, M. How do humans sketch objects? ACM Transactions on Graphics Vol. 31, No. 4, Article No. 44, 2012.","DOI":"10.1145\/2185520.2185540"},{"key":"234_CR89","doi-asserted-by":"crossref","unstructured":"Caesar, H.; Uijlings, J.; Ferrari, V. COCO-stuff: Thing and stuff classes in context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1209\u20131218, 2018.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"234_CR90","doi-asserted-by":"crossref","unstructured":"Huang, X.; Belongie, S. Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, 1510\u20131519, 2017.","DOI":"10.1109\/ICCV.2017.167"},{"key":"234_CR91","doi-asserted-by":"crossref","unstructured":"Zhu, P. H.; Abdal, R.; Qin, Y. P.; Wonka, P. SEAN: Image synthesis with semantic region-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5103\u20135112, 2020.","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"234_CR92","doi-asserted-by":"crossref","unstructured":"Yu, Q.; Liu, F.; Song, Y. Z.; Xiang, T.; Hospedales, T. M.; Loy, C. C. Sketch me that shoe. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 799\u2013807, 2016.","DOI":"10.1109\/CVPR.2016.93"},{"key":"234_CR93","doi-asserted-by":"crossref","unstructured":"Krause, J.; Stark, M.; Jia, D.; Li, F. F. 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, 554\u2013561, 2013.","DOI":"10.1109\/ICCVW.2013.77"},{"key":"234_CR94","doi-asserted-by":"crossref","unstructured":"Yu, A.; Grauman, K. Fine-grained visual comparisons with local learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 192\u2013199, 2014.","DOI":"10.1109\/CVPR.2014.32"},{"key":"234_CR95","doi-asserted-by":"crossref","unstructured":"Yu, A.; Grauman, K. Semantic jitter: Dense supervision for visual comparisons via synthetic images. In: Proceedings of the IEEE International Conference on Computer Vision, 5571\u20135580, 2017.","DOI":"10.1109\/ICCV.2017.594"},{"key":"234_CR96","doi-asserted-by":"crossref","unstructured":"Liu, Z. W.; Luo, P.; Wang, X. G.; Tang, X. O. Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, 3730\u20133738, 2015.","DOI":"10.1109\/ICCV.2015.425"},{"key":"234_CR97","unstructured":"Karras, T.; Aila, T.; Laine, S.; Lehtinen, J. Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196, 2017."},{"issue":"11","key":"234_CR98","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1109\/TPAMI.2008.222","volume":"31","author":"X G Wang","year":"2009","unstructured":"Wang, X. G.; Tang, X. O. Face photo-sketch synthesis and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 31, No. 11, 1955\u20131967, 2009.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"234_CR99","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1111\/j.1467-8659.2006.00960.x","volume":"25","author":"M Johnson","year":"2006","unstructured":"Johnson, M.; Brostow, G. J.; Shotton, J.; Arandjelovic, O.; Kwatra, V.; Cipolla, R. Semantic photo synthesis. Computer Graphics Forum Vol. 25, No. 3, 407\u2013413, 2006.","journal-title":"Computer Graphics Forum"},{"key":"234_CR100","doi-asserted-by":"crossref","unstructured":"Bansal, A.; Sheikh, Y.; Ramanan, D. Shapes and context: In-the-wild image synthesis & manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2312\u20132321, 2019.","DOI":"10.1109\/CVPR.2019.00242"},{"key":"234_CR101","doi-asserted-by":"crossref","unstructured":"Chen, Q. F.; Koltun, V. Photographic image synthesis with cascaded refinement networks. In: Proceedings of the IEEE International Conference on Computer Vision, 1520\u20131529, 2017.","DOI":"10.1109\/ICCV.2017.168"},{"key":"234_CR102","doi-asserted-by":"crossref","unstructured":"Lassner, C.; Pons-Moll, G.; Gehler, P. V. A generative model of people in clothing. In: Proceedings of the IEEE International Conference on Computer Vision, 853\u2013862, 2017.","DOI":"10.1109\/ICCV.2017.98"},{"key":"234_CR103","doi-asserted-by":"crossref","unstructured":"Park, T.; Liu, M. Y.; Wang, T. C.; Zhu, J. Y. Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2332\u20132341, 2019.","DOI":"10.1109\/CVPR.2019.00244"},{"key":"234_CR104","unstructured":"Liu, X.; Yin, G.; Shao, J.; Wang, X.; Li, H. Learning to predict layout-to-image conditional convolutions for semantic image synthesis. In: Proceedings of the 33rd Conference on Neural Information Processing Systems, 570\u2013580, 2019."},{"key":"234_CR105","doi-asserted-by":"crossref","unstructured":"Zhu, Z.; Xu, Z. L.; You, A. S.; Bai, X. Semantically multi-modal image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5466\u20135475, 2020.","DOI":"10.1109\/CVPR42600.2020.00551"},{"key":"234_CR106","doi-asserted-by":"crossref","unstructured":"Tang, H.; Xu, D.; Yan, Y.; Torr, P. H. S.; Sebe, N. Local class-specific and global imagelevel generative adversarial networks for semantic-guided scene generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 7867\u20137876, 2020.","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"234_CR107","doi-asserted-by":"crossref","unstructured":"Qi, X. J.; Chen, Q. F.; Jia, J. Y.; Koltun, V. Semi-parametric image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8808\u20138816, 2018.","DOI":"10.1109\/CVPR.2018.00918"},{"key":"234_CR108","doi-asserted-by":"crossref","unstructured":"Wang, M.; Yang, G. Y.; Li, R. L.; Liang, R. Z.; Zhang, S. H.; Hall, P. M.; Hu, S.-M. Example-guided style-consistent image synthesis from semantic labeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1495\u20131504, 2019.","DOI":"10.1109\/CVPR.2019.00159"},{"issue":"12","key":"234_CR109","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1109\/TPAMI.2015.2408360","volume":"37","author":"X D Liang","year":"2015","unstructured":"Liang, X. D.; Liu, S.; Shen, X. H.; Yang, J. C.; Liu, L. Q.; Dong, J.; Lin, L.; Yan, S. C. Deep human parsing with active template regression. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 37, No. 12, 2402\u20132414, 2015.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"234_CR110","doi-asserted-by":"crossref","unstructured":"Liang, X. D.; Xu, C. Y.; Shen, X. H.; Yang, J. C.; Liu, S.; Tang, J. H.; Lin, L.; Yan, S. C. Human parsing with contextualized convolutional neural network. In: Proceedings of the IEEE International Conference on Computer Vision, 1386\u20131394, 2015.","DOI":"10.1109\/ICCV.2015.163"},{"key":"234_CR111","doi-asserted-by":"crossref","unstructured":"Liu, Z. W.; Luo, P.; Qiu, S.; Wang, X. G.; Tang, X. O. DeepFashion: Powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1096\u20131104, 2016.","DOI":"10.1109\/CVPR.2016.124"},{"key":"234_CR112","doi-asserted-by":"crossref","unstructured":"Lee, C. H.; Liu, Z. W.; Wu, L. Y.; Luo, P. MaskGAN: Towards diverse and interactive facial image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5548\u20135557, 2020.","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"234_CR113","doi-asserted-by":"crossref","unstructured":"Zhou, B. L.; Zhao, H.; Puig, X.; Fidler, S.; Barriuso, A.; Torralba, A. Semantic understanding of scenes through the ADE20K dataset. arXiv preprint arXiv:1608.05442, 2016.","DOI":"10.1109\/CVPR.2017.544"},{"key":"234_CR114","doi-asserted-by":"crossref","unstructured":"Zhou, B. L.; Zhao, H.; Puig, X.; Fidler, S.; Barriuso, A.; Torralba, A. Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5122\u20135130, 2017.","DOI":"10.1109\/CVPR.2017.544"},{"key":"234_CR115","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2014 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N.; Hoiem, D.; Kohli, P.; Fergus, R. Indoor segmentation and support inference from RGBD images. In: Computer Vision \u2014 ECCV 2012. Lecture Notes in Computer Science, Vol. 7576. Fitzgibbon, A.; Lazebnik, S.; Perona, P.; Sato, Y.; Schmid, C. Eds. Springer Berlin Heidelberg, 746\u2013760, 2012."},{"key":"234_CR116","doi-asserted-by":"crossref","unstructured":"Cordts, M.; Omran, M.; Ramos, S.; Rehfeld, T.; Enzweiler, M.; Benenson, R.; Franke, U.; Roth, S.; Schiele B. The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3213\u20133223, 2016.","DOI":"10.1109\/CVPR.2016.350"},{"key":"234_CR117","doi-asserted-by":"crossref","unstructured":"Bem, R. D.; Ghosh, A.; Boukhayma, A.; Ajanthan, T.; Siddharth, N.; Torr, P. A conditional deep generative model of people in natural images. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1449\u20131458, 2019.","DOI":"10.1109\/WACV.2019.00159"},{"issue":"4","key":"234_CR118","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L C Chen","year":"2018","unstructured":"Chen, L. C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A. L. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 4, 834\u2013848, 2018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"234_CR119","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2014 ECCV 2018","author":"L C Chen","year":"2018","unstructured":"Chen, L. C.; Zhu, Y. K.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11211. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 833\u2013851, 2018."},{"key":"234_CR120","doi-asserted-by":"crossref","unstructured":"Balakrishnan, G.; Zhao, A.; Dalca, A. V.; Durand, F.; Guttag, J. Synthesizing images of humans in unseen poses. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8340\u20138348, 2018.","DOI":"10.1109\/CVPR.2018.00870"},{"key":"234_CR121","doi-asserted-by":"crossref","unstructured":"Pumarola, A.; Agudo, A.; Sanfeliu, A.; Moreno-Noguer, F. Unsupervised person image synthesis in arbitrary poses. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8620\u20138628, 2018.","DOI":"10.1109\/CVPR.2018.00899"},{"key":"234_CR122","unstructured":"Dong, H.; Liang, X.; Gong, K.; Lai, H.; Zhu, J.; Yin, J. Soft-gated warping-GAN for pose-guided person image synthesis. In: Proceedings of the 32nd Conference on Neural Information Processing Systems, 474\u2013484, 2018."},{"key":"234_CR123","doi-asserted-by":"crossref","unstructured":"Li, Y. N.; Huang, C.; Loy, C. C. Dense intrinsic appearance flow for human pose transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3688\u20133697, 2019.","DOI":"10.1109\/CVPR.2019.00381"},{"key":"234_CR124","doi-asserted-by":"crossref","unstructured":"Zheng, L.; Shen, L. Y.; Tian, L.; Wang, S. J.; Wang, J. D.; Tian, Q. Scalable person re-identification: A benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, 1116\u20131124, 2015.","DOI":"10.1109\/ICCV.2015.133"},{"key":"234_CR125","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-319-46493-0_47","volume-title":"Computer Vision \u2014 ECCV 2016","author":"X C Yan","year":"2016","unstructured":"Yan, X. C.; Yang, J. M.; Sohn, K.; Lee, H. Attribute2Image: Conditional image generation from visual attributes. In: Computer Vision \u2014 ECCV 2016. Lecture Notes in Computer Science, Vol. 9908. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 776\u2013791, 2016."},{"key":"234_CR126","unstructured":"Huang, G. B.; Ramesh, M.; Berg, T.; Learned-Miller, E. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07\u201349. University of Massachusetts, 2007."},{"issue":"11","key":"234_CR127","doi-asserted-by":"publisher","first-page":"5464","DOI":"10.1109\/TIP.2019.2916751","volume":"28","author":"Z L He","year":"2019","unstructured":"He, Z. L.; Zuo, W. M.; Kan, M. N.; Shan, S. G.; Chen, X. L. AttGAN: Facial attribute editing by only changing what you want. IEEE Transactions on Image Processing Vol. 28, No. 11, 5464\u20135478, 2019.","journal-title":"IEEE Transactions on Image Processing"},{"key":"234_CR128","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1007\/978-3-030-01231-1_26","volume-title":"Computer Vision \u2014 ECCV 2018","author":"G Zhang","year":"2018","unstructured":"Zhang, G.; Kan, M. N.; Shan, S. G.; Chen, X. L. Generative adversarial network with spatial attention for face attribute editing. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11210. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 422\u2013437, 2018."},{"key":"234_CR129","doi-asserted-by":"crossref","unstructured":"Qian, S. J.; Lin, K. Y.; Wu, W.; Liu, Y.; Wang, Q.; Shen, F. M.; Qian, C.; He, R. Make a face: Towards arbitrary high fidelity face manipulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10032\u201310041, 2019.","DOI":"10.1109\/ICCV.2019.01013"},{"key":"234_CR130","doi-asserted-by":"crossref","unstructured":"Men, Y. F.; Mao, Y. M.; Jiang, Y. N.; Ma, W. Y.; Lian, Z. H. Controllable person image synthesis with attribute-decomposed GAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5083\u20135092, 2020.","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"234_CR131","doi-asserted-by":"crossref","unstructured":"Lee, H.; Lee, S. G. Fashion attributes-to-image synthesis using attention-based generative adversarial network. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 462\u2013470, 2019.","DOI":"10.1109\/WACV.2019.00055"},{"key":"234_CR132","unstructured":"Dinh, L.; Sohl-Dickstein, J.; Bengio, S. Density estimation using real NVP. arXiv preprint arXiv: 1605.08803, 2016."},{"key":"234_CR133","doi-asserted-by":"crossref","unstructured":"Zhao, B.; Meng, L. L.; Yin, W. D.; Sigal, L. Image generation from layout. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8576\u20138585, 2019.","DOI":"10.1109\/CVPR.2019.00878"},{"key":"234_CR134","doi-asserted-by":"crossref","unstructured":"Luo, A.; Zhang, Z. T.; Wu, J. J.; Tenenbaum, J. B. End-to-end optimization of scene layout. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3753\u20133762, 2020.","DOI":"10.1109\/CVPR42600.2020.00381"},{"key":"234_CR135","doi-asserted-by":"crossref","unstructured":"Song, S. R.; Yu, F.; Zeng, A.; Chang, A. X.; Savva, M.; Funkhouser, T. Semantic scene completion from a single depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 190\u2013198, 2017.","DOI":"10.1109\/CVPR.2017.28"},{"key":"234_CR136","doi-asserted-by":"crossref","unstructured":"Choi, Y.; Choi, M.; Kim, M.; Ha, J. W.; Kim, S.; Choo, J. StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8789\u20138797, 2018.","DOI":"10.1109\/CVPR.2018.00916"},{"key":"234_CR137","unstructured":"Vahdat, A.; Kautz, J. NVAE: A deep hierarchical variational autoencoder. In: Proceedings of the 34th Conference on Neural Information Processing Systems, 2020."},{"key":"234_CR138","unstructured":"Zhang, H.; Goodfellow, I. J.; Metaxas, D.; Odena, A. Self-attention generative adversarial networks. In: Proceedings of the International Conference on Machine Learning, 7354\u20137363, 2019."},{"key":"234_CR139","unstructured":"De Vries, H.; Strub, F.; Mary, J.; Larochelle, H.; Pietquin, O.; Courville A. Modulating early visual processing by language. In: Proceedings of the 30th Conference on Neural Information Processing Systems 6594\u20136604, 2017."},{"key":"234_CR140","unstructured":"Miyato, T.; Kataoka, T.; Koyama, M.; Yoshida, Y. Spectral normalization for generative adversarial networks. In: Proceedings of the International Conference on Learning Representations, 2018."},{"key":"234_CR141","first-page":"214","volume":"70","author":"M Arjovsky","year":"2017","unstructured":"Arjovsky, M.; Chintala, S.; Bottou, L. Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning, Vol. 70, 214\u2013223, 2017.","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"234_CR142","unstructured":"Gulrajani, I.; Ahmed, F.; Arjovsky, M.; Dumoulin, V.; Courville, A. C. Improved training of Wasserstein GANs. In: Proceedings of the 30th Conference on Neural Information Processing Systems, 5767\u20135777, 2017."},{"key":"234_CR143","doi-asserted-by":"crossref","unstructured":"Mao, X. D.; Li, Q.; Xie, H. R.; Lau, R. Y. K.; Wang, Z.; Smolley, S. P. Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, 2813\u20132821, 2017.","DOI":"10.1109\/ICCV.2017.304"},{"key":"234_CR144","unstructured":"Lim, J. H.; Ye, J. C. Geometric GAN. arXiv preprint arXiv:1705.02894, 2017."},{"key":"234_CR145","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2014 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J.; Alahi, A.; Li, F. F. Perceptual losses for real-time style transfer and super-resolution. In: Computer Vision \u2014 ECCV 2016. Lecture Notes in Computer Science, Vol. 9906. Leibem, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 694\u2013711, 2016."},{"key":"234_CR146","unstructured":"Velifickovific, P.; Cucurull, G.; Casanova, A.; Romero, A.; Lifio, P.; Bengio, Y. Graph attention networks. In: Proceedings of the International Conference on Learning Representations, 2018."},{"issue":"7","key":"234_CR147","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C.; Papava, D.; Olaru, V.; Sminchisescu, C. Human3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 36, No. 7, 1325\u20131339, 2014.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"234_CR148","doi-asserted-by":"crossref","unstructured":"Li, Y. T.; Gan, Z.; Shen, Y. L.; Liu, J. J.; Cheng, Y.; Wu, Y. X.; Carin, L.; Carlson, D.; Gao, J. F. StoryGAN: A sequential conditional GAN for story visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6322\u20136331, 2019.","DOI":"10.1109\/CVPR.2019.00649"},{"key":"234_CR149","doi-asserted-by":"crossref","unstructured":"Pan, Y. W.; Qiu, Z. F.; Yao, T.; Li, H. Q.; Mei, T. To create what you tell: Generating videos from captions. In: Proceedings of the 25th ACM international Conference on Multimedia, 1789\u20131798, 2017.","DOI":"10.1145\/3123266.3127905"},{"key":"234_CR150","doi-asserted-by":"crossref","unstructured":"Li, Y.; Min, M. R.; Shen, D.; Carlson, D.; Carin, L. Video generation from text. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"234_CR151","doi-asserted-by":"crossref","unstructured":"Wang, M.; Yang, G.-W.; Hu, S.-M.; Yau, S.-T.; Shamir, A. Write-a-video: Computational video montage from themed text. ACM Transactions on Graphics Vol. 38, No. 6, Article No. 177, 2019.","DOI":"10.1145\/3355089.3356520"},{"key":"234_CR152","doi-asserted-by":"crossref","unstructured":"Chen, L. L.; Maddox, R. K.; Duan, Z. Y.; Xu, C. L. Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 7824\u20137833, 2019.","DOI":"10.1109\/CVPR.2019.00802"},{"key":"234_CR153","doi-asserted-by":"publisher","first-page":"9299","DOI":"10.1609\/aaai.v33i01.33019299","volume":"33","author":"H Zhou","year":"2019","unstructured":"Zhou, H.; Liu, Y.; Liu, Z. W.; Luo, P.; Wang, X. G. Talking face generation by adversarially disentangled audio-visual representation. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 33, 9299\u20139306, 2019.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"12","key":"234_CR154","doi-asserted-by":"publisher","first-page":"3457","DOI":"10.1109\/TVCG.2020.3023573","volume":"26","author":"X Wen","year":"2020","unstructured":"Wen, X.; Wang, M.; Richardt, C.; Chen, Z. Y.; Hu, S. M. Photorealistic audio-driven video portraits. IEEE Transactions on Visualization and Computer Graphics Vol. 26, No. 12, 3457\u20133466, 2020.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"234_CR155","unstructured":"Mescheder, L.; Nowozin, S.; Geiger, A. Adversarial variational bayes: Unifying variational autoencoders and generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning, 2391\u20132400, 2017."}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0234-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41095-021-0234-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0234-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897562\/10897565.pdf?arnumber=10897565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:40Z","timestamp":1762367920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":155,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1007\/s41095-021-0234-8","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"type":"electronic","value":"2096-0662"},{"type":"print","value":"2096-0433"}],"subject":[],"published":{"date-parts":[[2022,3]]},"assertion":[{"value":"25 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}