{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:12:21Z","timestamp":1784038341426,"version":"3.55.0"},"reference-count":48,"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\/s41095-021-0228-6","type":"journal-article","created":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T12:03:16Z","timestamp":1635336196000},"page":"135-148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Reference-guided structure-aware deep sketch colorization for cartoons"],"prefix":"10.26599","volume":"8","author":[{"given":"Xueting","family":"Liu","sequence":"first","affiliation":[{"name":"Caritas Institute of Higher Education, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenliang","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen 518060, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengze","family":"Li","sequence":"additional","affiliation":[{"name":"Caritas Institute of Higher Education, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen 518060, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huisi","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen 518060, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"228_CR1","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":"228_CR2","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y.; Park, T.; Isola, P.; Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, 2242\u20132251, 2017.","DOI":"10.1109\/ICCV.2017.244"},{"key":"228_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision-ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R.; Isola, P.; Efros, A. A. Colorful image colorization. In: Computer Vision-ECCV 2016. Lecture Notes in Computer Science, Vol 9907. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 649\u2013666, 2016."},{"key":"228_CR4","unstructured":"Yonetsuji, T. Paints chainer. 2017. Available at https:\/\/github.com\/pfnet\/Paintschainer."},{"key":"228_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, L.; Ji, Y.; Lin, X.; Liu, C. P. Style transfer for anime sketches with enhanced residual U-net and auxiliary classifier GAN. In: Proceedings of the 4th IAPR Asian Conference on Pattern Recognition, 506\u2013511, 2017.","DOI":"10.1109\/ACPR.2017.61"},{"key":"228_CR6","doi-asserted-by":"crossref","unstructured":"Kim, H.; Jhoo, H. Y.; Park, E.; Yoo, S. Tag2Pix: Line art colorization using text tag with SECat and changing loss. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9055\u20139064, 2019.","DOI":"10.1109\/ICCV.2019.00915"},{"key":"228_CR7","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":"228_CR8","unstructured":"Li, Y.; Fang, C.; Yang, J.; Wang, Z.; Lu, X.; Yang, M. Universal style transfer via feature transforms. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 385\u2013395, 2017."},{"key":"228_CR9","unstructured":"Gonzalez-Garcia, A.; van de Weijer, J.; Bengio, Y. Image-to-image translation for cross-domain disentanglement. In: Proceedings of the 33rd Conference on Neural Information Processing Systems, 1294\u20131305, 2018."},{"key":"228_CR10","unstructured":"Yu, X.; Chen, Y.; Liu, S.; Li, T.; Li, G. Multi-mapping image-to-image translation via learning disentanglement. In: Proceedings of the 33rd Conference on Neural Information Processing Systems, 2990\u20132999, 2019."},{"issue":"2","key":"228_CR11","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s41095-015-0013-5","volume":"1","author":"X J Li","year":"2015","unstructured":"Li, X. J.; Zhao, H. L.; Nie, G. Z.; Huang, H. Image recoloring using geodesic distance based color harmonization. Computational Visual Media Vol. 1, No. 2, 143\u2013155, 2015.","journal-title":"Computational Visual Media"},{"issue":"1","key":"228_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s41095-015-0002-8","volume":"1","author":"Y W Miao","year":"2015","unstructured":"Miao, Y. W.; Hu, F. X.; Zhang, X. D.; Chen, J. Z.; Pajarola, R. SymmSketch: Creating symmetric 3D free-form shapes from 2D sketches. Computational Visual Media Vol. 1, No. 1, 3\u201316, 2015.","journal-title":"Computational Visual Media"},{"issue":"1","key":"228_CR13","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s41095-016-0066-0","volume":"3","author":"H Todo","year":"2017","unstructured":"Todo, H.; Yamaguchi, Y. Estimating reflectance and shape of objects from a single cartoon-shaded image. Computational Visual Media Vol. 3, No. 1, 21\u201331, 2017.","journal-title":"Computational Visual Media"},{"key":"228_CR14","doi-asserted-by":"crossref","unstructured":"Hertzmann, A.; Jacobs, C. E.; Oliver, N.; Curless, B.; Salesin, D. H. Image analogies. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, 327\u2013340, 2001.","DOI":"10.1145\/383259.383295"},{"key":"228_CR15","doi-asserted-by":"crossref","unstructured":"Gatys, L. A.; Ecker, A. S.; Bethge, M. Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2414\u20132423, 2016.","DOI":"10.1109\/CVPR.2016.265"},{"key":"228_CR16","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. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 694\u2013711, 2016."},{"key":"228_CR17","first-page":"715","volume":"11212","author":"A Sanakoyeu","year":"2018","unstructured":"Sanakoyeu, A.; Kotovenko, D.; Lang, S.; Ommer, B. A style-aware content loss for real-time HD style transfer. In: Proceedings of the European Conference on Computer Vision, Vol. 11212, 715\u2013731, 2018.","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"228_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, Y. L.; Fang, C.; Wang, Y. L.; Wang, Z. W.; Lin, Z.; Fu, Y.; Yang, J. Multimodal style transfer via graph cuts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 5942\u20135950, 2019.","DOI":"10.1109\/ICCV.2019.00604"},{"key":"228_CR19","unstructured":"Song, C.; Wu, Z.; Zhou, Y.; Gong, M.; Huang, H. ETNet: Error transition network for arbitrary style transfer. In: Proceedings of the Advances in Neural Information Processing Systems, 668\u2013677, 2019."},{"key":"228_CR20","doi-asserted-by":"crossref","unstructured":"Wang, H.; Li, Y. J.; Wang, Y. H.; Hu, H. J.; Yang, M. H. Collaborative distillation for ultraresolution universal style transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1857\u20131866, 2020.","DOI":"10.1109\/CVPR42600.2020.00193"},{"key":"228_CR21","doi-asserted-by":"crossref","unstructured":"Li, X.; Liu, S.; Kautz, J.; Yang, M. Learning linear transformations for fast arbitrary style transfer. arXiv preprint arXiv: 1808.04537, 2018.","DOI":"10.1109\/CVPR.2019.00393"},{"key":"228_CR22","doi-asserted-by":"crossref","unstructured":"Gao, W.; Li, Y. J.; Yin, Y. H.; Yang, M. H. Fast video multi-style transfer. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 3211\u20133219, 2020.","DOI":"10.1109\/WACV45572.2020.9093420"},{"issue":"11","key":"228_CR23","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial networks. Communications of the ACM Vol. 63, No. 11, 139\u2013144, 2020","journal-title":"Communications of the ACM"},{"key":"228_CR24","unstructured":"Kim, T.; Cha, M.; Kim, H.; Lee, J. K.; Kim, J. Learning to discover cross-domain relations with generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning, 1857\u20131865, 2017."},{"key":"228_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, L.; Li, C. Z.; Wong, T. T.; Ji, Y.; Liu, C. P. Two-stage sketch colorization. ACM Transactions on Graphics Vol. 37, No. 6, Article No. 261, 2019.","DOI":"10.1145\/3272127.3275090"},{"key":"228_CR26","unstructured":"Zhu, J.-Y.; Zhang, R.; Pathak, D.; Darrell, T.; Efros, A. A.; Wang, O.; Shechtman, E. Toward multimodal image-to-image translation. In: Proceedings of the 31st Conference on Neural Information Processing Systems, 465\u2013476, 2017."},{"key":"228_CR27","doi-asserted-by":"crossref","unstructured":"Lee, J.; Kim, E.; Lee, Y.; Kim, D.; Chang, J.; Choo, J. Reference-based sketch image colorization using augmented-self reference and dense semantic correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5800\u20135809, 2020.","DOI":"10.1109\/CVPR42600.2020.00584"},{"key":"228_CR28","doi-asserted-by":"crossref","unstructured":"Welsh, T.; Ashikhmin, M.; Mueller, K. Transferring color to greyscale images. In: Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, 277\u2013280, 2002.","DOI":"10.1145\/566654.566576"},{"issue":"1","key":"228_CR29","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1109\/TIP.2013.2288929","volume":"23","author":"A Bugeau","year":"2014","unstructured":"Bugeau, A.; Ta, V. T.; Papadakis, N. Variational exemplar-based image colorization. IEEE Transactions on Image Processing Vol. 23, No. 1, 298\u2013307, 2014.","journal-title":"IEEE Transactions on Image Processing"},{"key":"228_CR30","doi-asserted-by":"crossref","unstructured":"Liu, X. P.; Wan, L.; Qu, Y. G.; Wong, T. T., Lin, S., Leung, C. S., Heng, P. A. Intrinsic colorization. In: Proceedings of the ACM SIGGRAPH Asia 2008 papers, Article No. 152, 2008.","DOI":"10.1145\/1457515.1409105"},{"key":"228_CR31","doi-asserted-by":"crossref","unstructured":"Chia, A. Y. S.; Zhuo, S. J.; Gupta, R. K.; Tai, Y. W.; Cho, S. Y.; Tan, P.; Lin, S. Semantic colorization with Internet images. ACM Transactions on Graphics Vol. 30, No. 6, Article No. 156, 2011.","DOI":"10.1145\/2070781.2024190"},{"key":"228_CR32","doi-asserted-by":"crossref","unstructured":"Gupta, R. K.; Chia, A. Y. S.; Rajan, D.; Ng, E. S.; Huang, Z. Y. Image colorization using similar images. In: Proceedings of the 20th ACM International Conference on Multimedia, 369\u2013378, 2012.","DOI":"10.1145\/2393347.2393402"},{"key":"228_CR33","unstructured":"Tai, Y. W.; Jia, J. Y.; Tang, C. K. Local color transfer via probabilistic segmentation by expectation-maximization. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 747\u2013754, 2005."},{"key":"228_CR34","doi-asserted-by":"crossref","unstructured":"He, M. M.; Chen, D. D.; Liao, J.; Sander, P. V.; Yuan, L. Deep exemplar-based colorization. ACM Transactions on Graphics Vol. 37, No. 4, Article No. 47, 2018.","DOI":"10.1145\/3197517.3201365"},{"key":"228_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, B.; He, M. M.; Liao, J.; Sander, P. V.; Yuan, L.; Bermak, A.; Chen, D. Deep exemplar-based video colorization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8052\u20138061, 2019.","DOI":"10.1109\/CVPR.2019.00824"},{"key":"228_CR36","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 \u2014 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 \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11207. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 179\u2013196, 2018."},{"key":"228_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-01246-5_3","volume-title":"Computer Vision \u2014 ECCV 2018","author":"H Y Lee","year":"2018","unstructured":"Lee, H. Y.; Tseng, H. Y.; Huang, J. B.; Singh, M.; Yang, M. H. Diverse image-to-image translation via disentangled representations. In: Computer Vision \u2014 ECCV 2018. Lecture Notes in Computer Science, Vol. 11205. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 36\u201352, 2018."},{"key":"228_CR38","doi-asserted-by":"crossref","unstructured":"He, K. M.; Zhang, X. Y.; Ren, S. Q.; Sun, J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"228_CR39","unstructured":"Ulyanov, D.; Vedaldi, A.; Lempitsky, V. Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022, 2016."},{"key":"228_CR40","unstructured":"Available at https:\/\/www.kaggle.com\/ktaebum\/anime-sketch-colorization-pair."},{"key":"228_CR41","unstructured":"Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"228_CR42","unstructured":"Miyato, T.; Kataoka, T.; Koyama, M.; Yoshida, Y. Spectral normalization for generative adversarial networks. In: Proceedings of the 6th International Conference on Learning Representations, 2018."},{"key":"228_CR43","unstructured":"Mescheder, L.; Geiger, A.; Nowozin, S. Which training methods for GANs do actually converge? In: Proceedings of the 35th International Conference on Machine Learning, 3478\u20133487, 2018."},{"key":"228_CR44","unstructured":"Kingma, D. P.; Ba, J. Adam: A method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations, 2015."},{"key":"228_CR45","doi-asserted-by":"crossref","unstructured":"Sun, T. H.; Lai, C. H.; Wong, S. K.; Wang, Y. S. Adversarial colorization of icons based on contour and color conditions. In: Proceedings of the 27th ACM International Conference on Multimedia, 683\u2013691, 2019.","DOI":"10.1145\/3343031.3351041"},{"issue":"4","key":"228_CR46","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"},{"issue":"3","key":"228_CR47","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1016\/0047-259X(82)90077-X","volume":"12","author":"D C Dowson","year":"1982","unstructured":"Dowson, D. C.; Landau, B. V. The Fr\u00e9chet distance between multivariate normal distributions. Journal of Multivariate Analysis Vol. 12, No. 3, 450\u2013455, 1982.","journal-title":"Journal of Multivariate Analysis"},{"key":"228_CR48","doi-asserted-by":"crossref","unstructured":"Iizuka, S.; Simo-Serra, E.; Ishikawa, H. Globally and locally consistent image completion. ACM Transactions on Graphics Vol. 36, No. 4, Article No. 107, 2017.","DOI":"10.1145\/3072959.3073659"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0228-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41095-021-0228-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0228-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897562\/10897572.pdf?arnumber=10897572","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\/10897572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":48,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1007\/s41095-021-0228-6","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2022,3]]},"assertion":[{"value":"21 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 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"}}]}}