{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:06:45Z","timestamp":1791320805550,"version":"4.3.1"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2016,7,11]],"date-time":"2016-07-11T00:00:00Z","timestamp":1468195200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2016,7,11]]},"abstract":"<jats:p>\n                    In this paper, we present a novel technique to simplify sketch drawings based on learning a series of convolution operators. In contrast to existing approaches that require vector images as input, we allow the more general and challenging input of rough raster sketches such as those obtained from scanning pencil sketches. We convert the rough sketch into a simplified version which is then amendable for vectorization. This is all done in a fully automatic way without user intervention. Our model consists of a fully convolutional neural network which, unlike most existing convolutional neural networks, is able to process images of any dimensions and aspect ratio as input, and outputs a simplified sketch which has the same dimensions as the input image. In order to teach our model to simplify, we present a new dataset of pairs of rough and simplified sketch drawings. By leveraging convolution operators in combination with efficient use of our proposed dataset, we are able to train our sketch simplification model. Our approach naturally overcomes the limitations of existing methods,\n                    <jats:italic>e.g.<\/jats:italic>\n                    , vector images as input and long computation time; and we show that meaningful simplifications can be obtained for many different test cases. Finally, we validate our results with a user study in which we greatly outperform similar approaches and establish the state of the art in sketch simplification of raster images.\n                  <\/jats:p>","DOI":"10.1145\/2897824.2925972","type":"journal-article","created":{"date-parts":[[2016,7,11]],"date-time":"2016-07-11T12:04:33Z","timestamp":1468238673000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":192,"title":["Learning to simplify"],"prefix":"10.1145","volume":"35","author":[{"given":"Edgar","family":"Simo-Serra","sequence":"first","affiliation":[{"name":"Waseda University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoshi","family":"Iizuka","sequence":"additional","affiliation":[{"name":"Waseda University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuma","family":"Sasaki","sequence":"additional","affiliation":[{"name":"Waseda University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Ishikawa","sequence":"additional","affiliation":[{"name":"Waseda University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2016,7,11]]},"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\/1187112.1187227"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1384429.1384456"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/192426.192496"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(98)00045-4"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12164"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383894.2383942"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344792"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A. Springenberg J. T. and Brox T. 2015. Learning to generate chairs with convolutional neural networks. In CVPR.  Dosovitskiy A. Springenberg J. T. and Brox T. 2015. Learning to generate chairs with convolutional neural networks. In CVPR .","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"e_1_2_2_11_1","volume-title":"Flownet: Learning optical flow with convolutional networks.","author":"Fischer P.","year":"2015"},{"key":"e_1_2_2_12_1","volume-title":"Workshop on Sketch-Based Interfaces and Modeling, 49--57","author":"Fi\u0161er J."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/356625.356627"},{"key":"e_1_2_2_14_1","volume-title":"Neocognitron: A hierarchical neural network capable of visual pattern recognition. Neural networks 1, 2, 119--130.","author":"Fukushima K.","year":"1988"},{"key":"e_1_2_2_15_1","volume-title":"Pacific Conference on Computer Graphics and Applications","author":"Grabli S.","year":"2004"},{"key":"e_1_2_2_16_1","unstructured":"Grimm C. and Joshi P. 2012. Just drawit: A 3d sketching system. In nternational Symposium on Sketch-Based Interfaces and Modeling 121--130.   Grimm C. and Joshi P. 2012. Just drawit: A 3d sketching system. In nternational Symposium on Sketch-Based Interfaces and Modeling 121--130."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.127"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/263407.263525"},{"key":"e_1_2_2_19_1","unstructured":"Ioffe S. and Szegedy C. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML.  Ioffe S. and Szegedy C. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML ."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1996.0484"},{"key":"e_1_2_2_21_1","unstructured":"Krizhevsky A. Sutskever I. and Hinton G. E. 2012. Imagenet classification with deep convolutional neural networks. In NIPS.  Krizhevsky A. Sutskever I. and Hinton G. E. 2012. Imagenet classification with deep convolutional neural networks. In NIPS ."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2512349.2512801"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818067"},{"key":"e_1_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Long J. Shelhamer E. and Darrell T. 2015. Fully convolutional networks for semantic segmentation. In CVPR.  Long J. Shelhamer E. and Darrell T. 2015. Fully convolutional networks for semantic segmentation. In CVPR .","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_2_26_1","unstructured":"Nair V. and Hinton G. E. 2010. Rectified linear units improve restricted boltzmann machines. In ICML 807--814.  Nair V. and Hinton G. E. 2010. Rectified linear units improve restricted boltzmann machines. In ICML 807--814."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2421636.2421640"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.105"},{"key":"e_1_2_2_30_1","unstructured":"Preim B. and Strothotte T. 1995. Tuning rendered line-drawings. In Winter School in Computer Graphics 227--237.  Preim B. and Strothotte T. 1995. Tuning rendered line-drawings. In Winter School in Computer Graphics 227--237."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-007-0160-5"},{"key":"e_1_2_2_32_1","first-page":"625","article-title":"Grouping curved lines","volume":"7","author":"Rosin P. L.","year":"1994","journal-title":"Machine Graphics and Vision"},{"key":"e_1_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Rumelhart D. Hinton G. and Williams R. 1986. Learning representations by back-propagating errors. In Nature.  Rumelhart D. Hinton G. and Williams R. 1986. Learning representations by back-propagating errors. In Nature .","DOI":"10.1038\/323533a0"},{"key":"e_1_2_2_34_1","unstructured":"Selinger P. 2003. Potrace: a polygon-based tracing algorithm. Potrace (online) http:\/\/potrace. sourceforge. net\/potrace.pdf (2009-07-01).  Selinger P. 2003. Potrace: a polygon-based tracing algorithm. Potrace (online) http:\/\/potrace. sourceforge. net\/potrace.pdf (2009-07-01) ."},{"key":"e_1_2_2_35_1","volume-title":"Deepcontour: A deep convolutional feature learned by positive-sharing loss for contour detection. In CVPR.","author":"Shen W.","year":"2015"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01151.x"},{"key":"e_1_2_2_37_1","unstructured":"Simonyan K. and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition. In ICLR.  Simonyan K. and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition. In ICLR ."},{"key":"e_1_2_2_38_1","volume-title":"ICLR Workshop Track.","author":"Springenberg J. T."},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/987657.987674"},{"key":"e_1_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Zeiler M. D. and Fergus R. 2014. Visualizing and understanding convolutional networks. In ECCV.  Zeiler M. D. and Fergus R. 2014. Visualizing and understanding convolutional networks. In ECCV .","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_2_2_41_1","unstructured":"Zeiler M. D. 2012. ADADELTA: an adaptive learning rate method. CoRR abs\/1212.5701.  Zeiler M. D. 2012. ADADELTA: an adaptive learning rate method. CoRR abs\/1212.5701."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/357994.358023"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2897824.2925972","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2897824.2925972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:55:05Z","timestamp":1750208105000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2897824.2925972"}},"subtitle":["fully convolutional networks for rough sketch cleanup"],"short-title":[],"issued":{"date-parts":[[2016,7,11]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,7,11]]}},"alternative-id":["10.1145\/2897824.2925972"],"URL":"https:\/\/doi.org\/10.1145\/2897824.2925972","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7,11]]},"assertion":[{"value":"2016-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}