{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:33:17Z","timestamp":1775230397770,"version":"3.50.1"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2018,1,10]],"date-time":"2018-01-10T00:00:00Z","timestamp":1515542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"JST ACT-I","award":["JPMJPR16UD and JPMJPR16U3"],"award-info":[{"award-number":["JPMJPR16UD and JPMJPR16U3"]}]},{"name":"JST CREST","award":["JPMJCR14D1"],"award-info":[{"award-number":["JPMJCR14D1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2018,2,28]]},"abstract":"<jats:p>We present an integral framework for training sketch simplification networks that convert challenging rough sketches into clean line drawings. Our approach augments a simplification network with a discriminator network, training both networks jointly so that the discriminator network discerns whether a line drawing is real training data or the output of the simplification network, which, in turn, tries to fool it. This approach has two major advantages: first, because the discriminator network learns the structure in line drawings, it encourages the output sketches of the simplification network to be more similar in appearance to the training sketches. Second, we can also train the networks with additional unsupervised data: by adding rough sketches and line drawings that are not corresponding to each other, we can improve the quality of the sketch simplification. Thanks to a difference in the architecture, our approach has advantages over similar adversarial training approaches in stability of training and the aforementioned ability to utilize unsupervised training data. We show how our framework can be used to train models that significantly outperform the state of the art in the sketch simplification task, despite using the same architecture for inference. We also present an approach to optimize for a single image, which improves accuracy at the cost of additional computation time. Finally, we show that, using the same framework, it is possible to train the network to perform the inverse problem, i.e., convert simple line sketches into pencil drawings, which is not possible using the standard mean squared error loss. We validate our framework with two user tests, in which our approach is preferred to the state of the art in sketch simplification 88.9% of the time.<\/jats:p>","DOI":"10.1145\/3132703","type":"journal-article","created":{"date-parts":[[2018,1,10]],"date-time":"2018-01-10T16:51:38Z","timestamp":1515603098000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":98,"title":["Mastering Sketching"],"prefix":"10.1145","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2544-8592","authenticated-orcid":false,"given":"Edgar","family":"Simo-Serra","sequence":"first","affiliation":[{"name":"Waseda University, Shinjuku, Tokyo"}]},{"given":"Satoshi","family":"Iizuka","sequence":"additional","affiliation":[{"name":"Waseda University, Shinjuku, Tokyo"}]},{"given":"Hiroshi","family":"Ishikawa","sequence":"additional","affiliation":[{"name":"Waseda University, Shinjuku, Tokyo"}]}],"member":"320","published-online":{"date-parts":[[2018,1,10]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1449715.1449740"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461964"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12164"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_2_2_5_1","volume-title":"Conference on Neural Information Processing Systems.","author":"Dosovitskiy Alexey","year":"2016"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925946"},{"key":"e_1_2_2_7_1","volume-title":"Workshop on Sketch-Based Interfaces and Modeling. 49--57","author":"Fi\u0161er Jakub","year":"2015"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90014-7"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_2_2_10_1","volume-title":"Conference on Neural Information Processing Systems.","author":"Goodfellow Ian","year":"2014"},{"key":"e_1_2_2_11_1","volume-title":"International Symposium on Sketch-Based Interfaces and Modeling. 121--130","author":"Grimm Cindy","year":"2012"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.127"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/263407.263525"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925974"},{"key":"e_1_2_2_15_1","volume-title":"International Conference on Machine Learning.","author":"Ioffe Sergey","year":"2015"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1274871.1274878"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_43"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2512349.2512801"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818067"},{"key":"e_1_2_2_23_1","volume-title":"International Symposium on Non-Photorealistic Animation and Rendering. 65--73","author":"Lu Cewu","year":"2012"},{"key":"e_1_2_2_24_1","volume-title":"Conference on Neural Image Processing Deep Learning Workshop.","author":"Mirza Mehdi","year":"2014"},{"key":"e_1_2_2_25_1","volume-title":"International Conference on Machine Learning. 807--814","author":"Nair Vinod"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2421636.2421640"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.105"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_2_2_30_1","volume-title":"International Conference on Learning Representations.","author":"Radford Alec","year":"2016"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_2_2_32_1","volume-title":"Conference on Neural Information Processing Systems.","author":"Salimans Tim","year":"2016"},{"key":"e_1_2_2_33_1","volume-title":"Retrieved","author":"Selinger Peter","year":"2003"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01151.x"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"e_1_2_2_36_1","volume-title":"Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15.1929--1958.","author":"Srivastava Nitish","year":"2014"},{"key":"e_1_2_2_37_1","volume-title":"International Conference on Learning Representations.","author":"Taigman Yaniv","year":"2017"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_20"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00410640"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_31"},{"key":"e_1_2_2_41_1","volume-title":"ADADELTA: An adaptive learning rate method. arXiv Preprint arXiv:1212.5701.","author":"Zeiler Matthew D.","year":"2012"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_16"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3132703","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3132703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:10:56Z","timestamp":1750212656000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3132703"}},"subtitle":["Adversarial Augmentation for Structured Prediction"],"short-title":[],"issued":{"date-parts":[[2018,1,10]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,2,28]]}},"alternative-id":["10.1145\/3132703"],"URL":"https:\/\/doi.org\/10.1145\/3132703","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1,10]]},"assertion":[{"value":"2017-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-01-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}