{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T18:13:51Z","timestamp":1758824031050,"version":"3.41.0"},"reference-count":24,"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"}],"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>\n            In this paper, we present a novel unsupervised learning method for pixelization. Due to the difficulty in creating pixel art, preparing the paired training data for supervised learning is impractical. Instead, we propose an unsupervised learning framework to circumvent such difficulty. We leverage the dual nature of the pixelization and depixelization, and model these two tasks in the same network in a bi-directional manner with the input itself as training supervision. These two tasks are modeled as a cascaded network which consists of three stages for different purposes.\n            <jats:italic>GridNet<\/jats:italic>\n            transfers the input image into multi-scale grid-structured images with different aliasing effects.\n            <jats:italic>PixelNet<\/jats:italic>\n            associated with\n            <jats:italic>GridNet<\/jats:italic>\n            to synthesize pixel arts with sharp edges and perceptually optimal local structures.\n            <jats:italic>DepixelNet<\/jats:italic>\n            connects the previous network and aims to recover the pixelized result to the original image. For the sake of unsupervised learning, the mirror loss is proposed to hold the reversibility of feature representations in the process. In addition, adversarial, L1, and gradient losses are involved in the network to obtain pixel arts by retaining color correctness and smoothness. We show that our technique can synthesize crisper and perceptually more appropriate pixel arts than state-of-the-art image downscaling methods. We evaluate the proposed method with extensive experiments on many images. The proposed method outperforms state-of-the-art methods in terms of visual quality and user preference.\n          <\/jats:p>","DOI":"10.1145\/3272127.3275082","type":"journal-article","created":{"date-parts":[[2018,11,28]],"date-time":"2018-11-28T19:16:10Z","timestamp":1543432570000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Deep unsupervised pixelization"],"prefix":"10.1145","volume":"37","author":[{"given":"Chu","family":"Han","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, and South China University of Technology"}]},{"given":"Qiang","family":"Wen","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Qianshu","family":"Zhu","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Yinjie","family":"Tan","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Guoqiang","family":"Han","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Tien-Tsin","family":"Wong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong and Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, SIAT"}]}],"member":"320","published-online":{"date-parts":[[2018,12,4]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/325165.325182"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2330147.2330154"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/358728.358731"},{"key":"e_1_2_2_6_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680.   Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680."},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2330147.2330153"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486042.2486044"},{"key":"e_1_2_2_10_1","volume-title":"Image-to-image translation with conditional adversarial networks. arXiv preprint","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. arXiv preprint ( 2017 ). Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2017. Image-to-image translation with conditional adversarial networks. arXiv preprint (2017)."},{"key":"e_1_2_2_11_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964994"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508370"},{"volume-title":"Computer Graphics Forum","author":"Kuo Ming-Hsun","key":"e_1_2_2_14_1","unstructured":"Ming-Hsun Kuo , Yong-Liang Yang , and Hung-Kuo Chu . 2016. Feature-Aware Pixel Art Animation . In Computer Graphics Forum , Vol. 35 . Wiley Online Library , 411--420. Ming-Hsun Kuo, Yong-Liang Yang, and Hung-Kuo Chu. 2016. Feature-Aware Pixel Art Animation. In Computer Graphics Forum, Vol. 35. Wiley Online Library, 411--420."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_2_16_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero . 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 ( 2014 ). Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_2_2_17_1","volume-title":"Conditional image synthesis with auxiliary classifier gans. arXiv preprint arXiv:1610.09585","author":"Odena Augustus","year":"2016","unstructured":"Augustus Odena , Christopher Olah , and Jonathon Shlens . 2016. Conditional image synthesis with auxiliary classifier gans. arXiv preprint arXiv:1610.09585 ( 2016 ). Augustus Odena, Christopher Olah, and Jonathon Shlens. 2016. Conditional image synthesis with auxiliary classifier gans. arXiv preprint arXiv:1610.09585 (2016)."},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766891"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1949.232969"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.241"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980239"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"e_1_2_2_23_1","volume-title":"Dualgan: Unsupervised dual learning for image-to-image translation. arXiv preprint","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. arXiv preprint (2017). Zili Yi, Hao Zhang, Ping Tan, and Minglun Gong. 2017. Dualgan: Unsupervised dual learning for image-to-image translation. arXiv preprint (2017)."},{"key":"e_1_2_2_24_1","volume-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593","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. arXiv preprint arXiv:1703.10593 ( 2017 ). Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593 (2017)."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275082","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3272127.3275082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:05Z","timestamp":1750207445000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3272127.3275082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,4]]},"references-count":24,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,12,31]]}},"alternative-id":["10.1145\/3272127.3275082"],"URL":"https:\/\/doi.org\/10.1145\/3272127.3275082","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"type":"print","value":"0730-0301"},{"type":"electronic","value":"1557-7368"}],"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"}}]}}