{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:47:48Z","timestamp":1783108068247,"version":"3.54.6"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2018,12,4]],"date-time":"2018-12-04T00:00:00Z","timestamp":1543881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"RGC General Research Fund","award":["CUHK14217516 and CUHK14201017"],"award-info":[{"award-number":["CUHK14217516 and CUHK14201017"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2018,12,31]]},"abstract":"<jats:p>Sketch or line art colorization is a research field with significant market demand. Different from photo colorization which strongly relies on texture information, sketch colorization is more challenging as sketches may not have texture. Even worse, color, texture, and gradient have to be generated from the abstract sketch lines. In this paper, we propose a semi-automatic learning-based framework to colorize sketches with proper color, texture as well as gradient. Our framework consists of two stages. In the first drafting stage, our model guesses color regions and splashes a rich variety of colors over the sketch to obtain a color draft. In the second refinement stage, it detects the unnatural colors and artifacts, and try to fix and refine the result. Comparing to existing approaches, this two-stage design effectively divides the complex colorization task into two simpler and goal-clearer subtasks. This eases the learning and raises the quality of colorization. Our model resolves the artifacts such as water-color blurring, color distortion, and dull textures.<\/jats:p>\n          <jats:p>We build an interactive software based on our model for evaluation. Users can iteratively edit and refine the colorization. We evaluate our learning model and the interactive system through an extensive user study. Statistics shows that our method outperforms the state-of-art techniques and industrial applications in several aspects including, the visual quality, the ability of user control, user experience, and other metrics.<\/jats:p>","DOI":"10.1145\/3272127.3275090","type":"journal-article","created":{"date-parts":[[2018,11,28]],"date-time":"2018-11-28T19:16:10Z","timestamp":1543432570000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":131,"title":["Two-stage sketch colorization"],"prefix":"10.1145","volume":"37","author":[{"given":"Lvmin","family":"Zhang","sequence":"first","affiliation":[{"name":"Soochow University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengze","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tien-Tsin","family":"Wong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Ji","sequence":"additional","affiliation":[{"name":"Soochow University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunping","family":"Liu","sequence":"additional","affiliation":[{"name":"Soochow University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,12,4]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks. CVPR","author":"Bousmalis Konstantinos","year":"2017","unstructured":"Konstantinos Bousmalis , Nathan Silberman , David Dohan , Dumitru Erhan , and Dilip Krishnan . 2017. Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks. CVPR ( 2017 ). Konstantinos Bousmalis, Nathan Silberman, David Dohan, Dumitru Erhan, and Dilip Krishnan. 2017. Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks. CVPR (2017)."},{"key":"e_1_2_2_2_1","volume-title":"Photographic Image Synthesis with Cascaded Refinement Networks. ICCV","author":"Chen Qifeng","year":"2017","unstructured":"Qifeng Chen and Vladlen Koltun . 2017. Photographic Image Synthesis with Cascaded Refinement Networks. ICCV ( 2017 ). Qifeng Chen and Vladlen Koltun. 2017. Photographic Image Synthesis with Cascaded Refinement Networks. ICCV (2017)."},{"key":"e_1_2_2_3_1","unstructured":"DanbooruCommunity. 2018. Danbooru2017: A Large-Scale Crowdsourced and Tagged Anime Illustration Dataset. (2018).  DanbooruCommunity. 2018. Danbooru2017: A Large-Scale Crowdsourced and Tagged Anime Illustration Dataset. (2018)."},{"key":"e_1_2_2_4_1","volume-title":"Adversarial Feature Learning. ICLR","author":"Donahue Jeff","year":"2017","unstructured":"Jeff Donahue , Philipp Kr\u00c3d'henb\u00c3ijhl , and Trevor Darrell . 2017. Adversarial Feature Learning. ICLR ( 2017 ). Jeff Donahue, Philipp Kr\u00c3d'henb\u00c3ijhl, and Trevor Darrell. 2017. Adversarial Feature Learning. ICLR (2017)."},{"key":"e_1_2_2_5_1","volume-title":"ImageNet: crowdsourcing, benchmarking & other cool things. CMU VASC Seminar","author":"Fei-Fei L.","year":"2010","unstructured":"L. Fei-Fei . 2010. ImageNet: crowdsourcing, benchmarking & other cool things. CMU VASC Seminar ( 2010 ). L. Fei-Fei. 2010. ImageNet: crowdsourcing, benchmarking & other cool things. CMU VASC Seminar (2010)."},{"key":"e_1_2_2_6_1","volume-title":"Arxiv","author":"Frans Kevin","year":"2017","unstructured":"Kevin Frans . 2017. Outline Colorization through Tandem Adversarial Networks . In Arxiv ( 2017 ). Kevin Frans. 2017. Outline Colorization through Tandem Adversarial Networks. In Arxiv (2017)."},{"key":"e_1_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Chie Furusawa Kazuyuki Hiroshiba Keisuke Ogaki and Yuri Odagiri. 2017. Comicolorization. In SIGGRAPH Asia 2017 Technical Briefs.  Chie Furusawa Kazuyuki Hiroshiba Keisuke Ogaki and Yuri Odagiri. 2017. Comicolorization. In SIGGRAPH Asia 2017 Technical Briefs.","DOI":"10.1145\/3145749.3149430"},{"key":"e_1_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Leon A. Gatys Alexander S. Ecker and Matthias Bethge. 2016. Image Style Transfer Using Convolutional Neural Networks. In CVPR. 2414--2423.  Leon A. Gatys Alexander S. Ecker and Matthias Bethge. 2016. Image Style Transfer Using Convolutional Neural Networks. In CVPR. 2414--2423.","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_2_2_9_1","first-page":"2672","article-title":"Generative Adversarial Networks","volume":"3","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow , Jean Pouget-Abadie , Mehdi Mirza , Bing Xu , David Warde-Farley , Sherjil Ozair , Aaron Courville , and Yoshua Bengio . 2014 . Generative Adversarial Networks . NIPS 3 (2014), 2672 -- 2680 . Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Networks. NIPS 3 (2014), 2672--2680.","journal-title":"NIPS"},{"key":"e_1_2_2_10_1","unstructured":"Christopher Hart. 2015. The Master Guide to Drawing Anime: How to Draw Original Characters from Simple Templates. Paperback.  Christopher Hart. 2015. The Master Guide to Drawing Anime: How to Draw Original Characters from Simple Templates. Paperback."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.295"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925974"},{"key":"e_1_2_2_13_1","volume-title":"Image-to-Image Translation with Conditional Adversarial Networks. CVPR","author":"Isola Phillip","year":"2017","unstructured":"Phillip Isola , Jun-Yan Zhu , Tinghui Zhou , and Alexei A Efros . 2017. Image-to-Image Translation with Conditional Adversarial Networks. CVPR ( 2017 ). Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2017. Image-to-Image Translation with Conditional Adversarial Networks. CVPR (2017)."},{"key":"e_1_2_2_14_1","volume-title":"Spatial Transformer Networks. NIPS","author":"Jaderberg Max","year":"2015","unstructured":"Max Jaderberg , Karen Simonyan , Andrew Zisserman , and Koray Kavukcuoglu . 2015. Spatial Transformer Networks. NIPS ( 2015 ). Max Jaderberg, Karen Simonyan, Andrew Zisserman, and Koray Kavukcuoglu. 2015. Spatial Transformer Networks. NIPS (2015)."},{"key":"e_1_2_2_15_1","volume-title":"Jung Kwon Lee, and Jiwon Kim","author":"Kim Taeksoo","year":"2017","unstructured":"Taeksoo Kim , Moonsu Cha , Hyunsoo Kim , Jung Kwon Lee, and Jiwon Kim . 2017 . Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. ICML ( 2017). Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, and Jiwon Kim. 2017. Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. ICML (2017)."},{"key":"e_1_2_2_16_1","volume-title":"Adam: A Method for Stochastic Optimization. Computer Science","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A Method for Stochastic Optimization. Computer Science (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. Computer Science (2014)."},{"key":"e_1_2_2_17_1","volume-title":"Learning Representations for Automatic Colorization","author":"Larsson Gustav","unstructured":"Gustav Larsson , Michael Maire , and Gregory Shakhnarovich . 2016. Learning Representations for Automatic Colorization . In ECCV. Springer , 577--593. Gustav Larsson, Michael Maire, and Gregory Shakhnarovich. 2016. Learning Representations for Automatic Colorization. In ECCV. Springer, 577--593."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073675"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073683"},{"key":"e_1_2_2_20_1","volume-title":"Unsupervised Image-to-Image Translation Networks. NIPS","author":"Liu Ming-Yu","year":"2017","unstructured":"Ming-Yu Liu , Thomas Breuel , and Jan Kautz . 2017a. Unsupervised Image-to-Image Translation Networks. NIPS ( 2017 ). Ming-Yu Liu, Thomas Breuel, and Jan Kautz. 2017a. Unsupervised Image-to-Image Translation Networks. NIPS (2017)."},{"key":"e_1_2_2_21_1","volume-title":"Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks. In Arxiv","author":"Liu Yifan","year":"2017","unstructured":"Yifan Liu , Zengchang Qin , Zhenbo Luo , and Hua Wang . 2017 b. Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks. In Arxiv (2017). Yifan Liu, Zengchang Qin, Zhenbo Luo, and Hua Wang. 2017b. Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks. In Arxiv (2017)."},{"key":"e_1_2_2_22_1","volume-title":"Hinton","author":"Nair Vinod","year":"2010","unstructured":"Vinod Nair and Geoffrey E . Hinton . 2010 . Rectified Linear Units Improve Restricted Boltzmann Machines. ICML ( 2010), 807--814. Vinod Nair and Geoffrey E. Hinton. 2010. Rectified Linear Units Improve Restricted Boltzmann Machines. ICML (2010), 807--814."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142017"},{"key":"e_1_2_2_24_1","volume-title":"Scribbler: Controlling Deep Image Synthesis with Sketch and Color. CVPR","author":"Sangkloy Patsorn","year":"2017","unstructured":"Patsorn Sangkloy , Jingwan Lu , Chen Fang , Fisher Yu , and James Hays . 2017 . Scribbler: Controlling Deep Image Synthesis with Sketch and Color. CVPR (2017). Patsorn Sangkloy, Jingwan Lu, Chen Fang, Fisher Yu, and James Hays. 2017. Scribbler: Controlling Deep Image Synthesis with Sketch and Color. CVPR (2017)."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132703"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201370"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"e_1_2_2_28_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science (2014)."},{"key":"e_1_2_2_29_1","volume-title":"LazyBrush: Flexible Painting Tool for Hand-drawn Cartoons. Computer Graphics Forum 28, 2","author":"Sykora Daniel","year":"2009","unstructured":"Daniel Sykora , John Dingliana , and Steven Collins . 2009. LazyBrush: Flexible Painting Tool for Hand-drawn Cartoons. Computer Graphics Forum 28, 2 ( 2009 ). Daniel Sykora, John Dingliana, and Steven Collins. 2009. LazyBrush: Flexible Painting Tool for Hand-drawn Cartoons. Computer Graphics Forum 28, 2 (2009)."},{"key":"e_1_2_2_30_1","volume-title":"Going Deeper with Convolutions. CVPR","author":"Szegedy Christian","year":"2015","unstructured":"Christian Szegedy , Wei Liu , Yangqing Jia , Pierre Sermanet , Scott E. Reed , Dragomir Anguelov , Dumitru Erhan , Vincent Vanhoucke , and Andrew Rabinovich . 2015. Going Deeper with Convolutions. CVPR ( 2015 ). Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott E. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going Deeper with Convolutions. CVPR (2015)."},{"key":"e_1_2_2_31_1","unstructured":"TaiZan. 2016. PaintsChainer Tanpopo. PreferredNetwork (2016).  TaiZan. 2016. PaintsChainer Tanpopo. PreferredNetwork (2016)."},{"key":"e_1_2_2_32_1","unstructured":"TaiZan. 2017a. PaintsChainer Canna. PreferredNetwork (2017).  TaiZan. 2017a. PaintsChainer Canna. PreferredNetwork (2017)."},{"key":"e_1_2_2_33_1","unstructured":"TaiZan. 2017b. PaintsChainer Satsuki. PreferredNetwork (2017).  TaiZan. 2017b. PaintsChainer Satsuki. PreferredNetwork (2017)."},{"key":"e_1_2_2_34_1","volume-title":"Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation. ECCV","author":"Wang Chao","year":"2018","unstructured":"Chao Wang , Haiyong Zheng , Zhibin Yu , Ziqiang Zheng , Zhaorui Gu , and Bing Zheng . 2018b. Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation. ECCV ( 2018 ). Chao Wang, Haiyong Zheng, Zhibin Yu, Ziqiang Zheng, Zhaorui Gu, and Bing Zheng. 2018b. Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation. ECCV (2018)."},{"key":"e_1_2_2_35_1","volume-title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs. CVPR","author":"Wang Ting-Chun","year":"2018","unstructured":"Ting-Chun Wang , Ming-Yu Liu , Jun-Yan Zhu , Andrew Tao , Jan Kautz , and Bryan Catanzaro . 2018a. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs. CVPR ( 2018 ). Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. 2018a. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs. CVPR (2018)."},{"key":"e_1_2_2_36_1","volume-title":"DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. ICCV","author":"Yi Zili","year":"2017","unstructured":"Zili Yi , Hao Zhang , Ping Tan , and Minglun Gong . 2017. DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. ICCV ( 2017 ). Zili Yi, Hao Zhang, Ping Tan, and Minglun Gong. 2017. DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. ICCV (2017)."},{"key":"e_1_2_2_37_1","volume-title":"Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN. ACPR","author":"Zhang Lvmin","year":"2017","unstructured":"Lvmin Zhang , Yi Ji , and Xin Lin . 2017a. Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN. ACPR ( 2017 ). Lvmin Zhang, Yi Ji, and Xin Lin. 2017a. Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN. ACPR (2017)."},{"key":"e_1_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola and Alexei A Efros. 2016. Colorful Image Colorization. In ECCV.  Richard Zhang Phillip Isola and Alexei A Efros. 2016. Colorful Image Colorization. In ECCV.","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073703"},{"key":"e_1_2_2_40_1","volume-title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. ICCV","author":"Zhu Jun-Yan","year":"2017","unstructured":"Jun-Yan Zhu , Taesung Park , Phillip Isola , and Alexei A Efros . 2017. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. ICCV ( 2017 ). Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. 2017. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. ICCV (2017)."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275090","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3272127.3275090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:26Z","timestamp":1750207466000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,4]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,12,31]]}},"alternative-id":["10.1145\/3272127.3275090"],"URL":"https:\/\/doi.org\/10.1145\/3272127.3275090","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,4]]},"assertion":[{"value":"2018-12-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}