{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:28:22Z","timestamp":1743035302320,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031258244"},{"type":"electronic","value":"9783031258251"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-25825-1_1","type":"book-chapter","created":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T19:02:52Z","timestamp":1675450972000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["StencilTorch: An Iterative and\u00a0User-Guided Framework for\u00a0Anime Lineart Colorization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1711-3194","authenticated-orcid":false,"given":"Yliess","family":"Hati","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2085-7258","authenticated-orcid":false,"given":"Vincent","family":"Thevenin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7198-2273","authenticated-orcid":false,"given":"Florent","family":"Nolot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9619-0122","authenticated-orcid":false,"given":"Francis","family":"Rousseaux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2727-789X","authenticated-orcid":false,"given":"Clement","family":"Duhart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,4]]},"reference":[{"key":"1_CR1","unstructured":"Anonymous, community, D., Branwen, G.: Danbooru 2020: A large-scale crowdsourced and tagged anime illustration dataset, January 2021. https:\/\/www.gwern.net\/Danbooru2020"},{"key":"1_CR2","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 214\u2013223. PMLR, International Convention Centre, Sydney, Australia, 06\u201311 Aug 2017. https:\/\/proceedings.mlr.press\/v70\/arjovsky17a.html"},{"key":"1_CR3","doi-asserted-by":"publisher","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41\u201348. ICML 2009, Association for Computing Machinery, New York, NY, USA (2009). https:\/\/doi.org\/10.1145\/1553374.1553380","DOI":"10.1145\/1553374.1553380"},{"key":"1_CR4","doi-asserted-by":"publisher","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1800\u20131807 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Ci, Y., Ma, X., Wang, Z., Li, H., Luo, Z.: User-guided deep anime line art colorization with conditional adversarial networks. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1536\u20131544. MM 2018, Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3240508.3240661","DOI":"10.1145\/3240508.3240661"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Elman, J.L.: Learning and development in neural networks: the importance of starting small. Cognition 48(1), 71\u201399 (1993)","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"1_CR7","unstructured":"Frans, K.: Outline colorization through tandem adversarial networks. CoRR abs\/1704.08834 (2017). arxiv:1704.08834"},{"key":"1_CR8","doi-asserted-by":"publisher","unstructured":"Furusawa, C., Hiroshiba, K., Ogaki, K., Odagiri, Y.: Comicolorization: semi-automatic manga colorization. In: SIGGRAPH Asia 2017 Technical Briefs, SA 2017, Association for Computing Machinery, New York, NY, USA (2017). https:\/\/doi.org\/10.1145\/3145749.3149430","DOI":"10.1145\/3145749.3149430"},{"key":"1_CR9","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, vol. 2, pp. 2672\u20132680. NIPS 2014, MIT Press, Cambridge, MA, USA (2014). https:\/\/dl.acm.org\/doi\/10.5555\/2969033.2969125"},{"key":"1_CR10","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017), https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/892c3b1c6dccd52936e27cbd0ff683d6-Paper.pdf"},{"key":"1_CR11","unstructured":"Hacohen, G., Weinshall, D.: On the power of curriculum learning in training deep networks. In: Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA. Proceedings of Machine Learning Research, vol. 97, pp. 2535\u20132544. PMLR (2019). https:\/\/proceedings.mlr.press\/v97\/hacohen19a.html"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Hati, Y., Jouet, G., Rousseaux, F., Duhart, C.: PaintsTorch: a user-guided anime line art colorization tool with double generator conditional adversarial network. In: European Conference on Visual Media Production. CVMP 2019, Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3359998.3369401","DOI":"10.1145\/3359998.3369401"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR14","doi-asserted-by":"publisher","unstructured":"Hensman, P., Aizawa, K.: CGAN-based manga colorization using a single training image. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 3, pp. 72\u201377. IEEE Computer Society, Los Alamitos, CA, USA, Nov 2017. https:\/\/doi.org\/10.1109\/ICDAR.2017.295, https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICDAR.2017.295","DOI":"10.1109\/ICDAR.2017.295"},{"key":"1_CR15","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, pp. 6629\u20136640. NIPS\u201917, Curran Associates Inc., Red Hook, NY, USA (2017)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","DOI":"10.1126\/science.1127647"},{"key":"1_CR17","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR18","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 37, pp. 448\u2013456. PMLR, Lille, France, 07\u201309 July 2015. https:\/\/proceedings.mlr.press\/v37\/ioffe15.html"},{"key":"1_CR19","unstructured":"Kandinsky, W., Sadleir, M.: Concerning the Spiritual in Art. Dover Publications, New York (1977). (oCLC: 3042682)"},{"key":"1_CR20","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. CoRR abs\/1710.10196 (2017). arxiv.org:1710.10196"},{"key":"1_CR21","doi-asserted-by":"publisher","unstructured":"Kim, H., Jhoo, H.Y., Park, E., Yoo, S.: Tag2pix: line art colorization using text tag with Secat and changing loss. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9055\u20139064 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00915","DOI":"10.1109\/ICCV.2019.00915"},{"key":"1_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14\u201316, 2014, Conference Track Proceedings (2014). arxiv.org:1312.6114"},{"key":"1_CR23","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: Generative flow with invertible 1 $$\\times $$ 1 convolutions. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","DOI":"10.1145\/3065386"},{"key":"1_CR25","unstructured":"Lim, J.H., Ye, J.C.: Geometric GAN (2017)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Qin, Z., Wan, T., Luo, Z.: Auto-painter: cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks. Neurocomputing 311, 78\u201387 (2018)","DOI":"10.1016\/j.neucom.2018.05.045"},{"key":"1_CR27","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam. CoRR abs\/1711.05101 (2017). arxiv.org:1711.05101"},{"key":"1_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-3-030-58601-0_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Ji, Y., Liu, C.: DanbooRegion: an illustration region dataset. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 137\u2013154. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_9"},{"key":"1_CR29","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"1_CR30","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. CoRR abs\/1802.05957 (2018). arxiv.org:1802.05957"},{"key":"1_CR31","unstructured":"Pixiv: Pelica Paint. https:\/\/petalica-paint.pixiv.dev\/index_en.html (2017)"},{"key":"1_CR32","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip LATENTs. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"1_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"1_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision (IJCV) 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"1_CR35","doi-asserted-by":"publisher","unstructured":"Saito, M., Matsui, Y.: Illustration2vec: a semantic vector representation of illustrations. In: SIGGRAPH Asia 2015 Technical Briefs, pp. 5:1\u20135:4. SA 2015, ACM, New York, NY, USA (2015). https:\/\/doi.org\/10.1145\/2820903.2820907","DOI":"10.1145\/2820903.2820907"},{"key":"1_CR36","doi-asserted-by":"publisher","unstructured":"Sangkloy, P., Lu, J., Fang, C., Yu, F., Hays, J.: Scribbler: controlling deep image synthesis with sketch and color. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 6836\u20136845. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.723","DOI":"10.1109\/CVPR.2017.723"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"1_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015). arxiv.org:1409.1556"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"1_CR41","doi-asserted-by":"publisher","unstructured":"Winnem\u00f6ller, H., Kyprianidis, J.E., Olsen, S.C.: XDOG: an extended difference-of-Gaussians compendium including advanced image stylization. Comput. Graph. 36(6), 740\u2013753 (2012). https:\/\/doi.org\/10.1016\/j.cag.2012.03.004, www.sciencedirect.com\/science\/article\/pii\/S009784931200043X, 2011 Joint Symposium on Computational Aesthetics (CAe), Non-Photorealistic Animation and Rendering (NPAR), and Sketch-Based Interfaces and Modeling (SBIM)","DOI":"10.1016\/j.cag.2012.03.004"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987\u20135995 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"1_CR43","doi-asserted-by":"publisher","unstructured":"Zhang, L., Ji, Y., Lin, X., Liu, C.: Style transfer for anime sketches with enhanced residual u-net and auxiliary classifier GAN. In: 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR), pp. 506\u2013511 (2017). https:\/\/doi.org\/10.1109\/ACPR.2017.61","DOI":"10.1109\/ACPR.2017.61"},{"key":"1_CR44","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"1_CR45","doi-asserted-by":"publisher","unstructured":"Zhang, R., et al.: Real-time user-guided image colorization with learned deep priors. ACM Trans. Graph. 36(4), 1\u201311 (2017). https:\/\/doi.org\/10.1145\/3072959.3073703","DOI":"10.1145\/3072959.3073703"}],"container-title":["Lecture Notes in Computer Science","Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25825-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T19:03:37Z","timestamp":1675451017000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25825-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031258244","9783031258251"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25825-1_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"4 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IVCNZ","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Vision Computing New Zealand","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ivcnz2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ivcnz2022.aut.ac.nz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.7","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.1","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}