{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:11:41Z","timestamp":1780589501864,"version":"3.54.1"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"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":[[2022,12]]},"abstract":"<jats:p>Colorization is multimodal by nature and challenges existing frameworks to achieve colorful and structurally consistent results. Even the sophisticated autoregressive model struggles to maintain long-distance color consistency due to the fragility of sequential dependence. To overcome this challenge, we propose a novel colorization framework that disentangles color multimodality and structure consistency through global color anchors, so that both aspects could be learned effectively. Our key insight is that several carefully located anchors could approximately represent the color distribution of an image, and conditioned on the anchor colors, we can predict the image color in a deterministic manner by utilizing internal correlation. To this end, we construct a colorization model with dual branches, where the color modeler predicts the color distribution for anchor color representation, and the color generator predicts the pixel colors by referring the sampled anchor colors. Importantly, the anchors are located under two principles: color independence and global coverage, which is realized with clustering analysis on the deep color features. To simplify the computation, we creatively adopt soft superpixel segmentation to reduce the image primitives, which still nicely reserves the reversibility to pixel-wise representation. Extensive experiments show that our method achieves notable superiority over various mainstream frameworks in perceptual quality. Thanks to anchor-based color representation, our model has the flexibility to support diverse and controllable colorization as well.<\/jats:p>","DOI":"10.1145\/3550454.3555432","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T21:19:07Z","timestamp":1669843147000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Disentangled Image Colorization via Global Anchors"],"prefix":"10.1145","volume":"41","author":[{"given":"Menghan","family":"Xia","sequence":"first","affiliation":[{"name":"Tecent AI Lab, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Hu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tien-Tsin","family":"Wong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jue","family":"Wang","sequence":"additional","affiliation":[{"name":"Tecent AI Lab, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"e_1_2_1_2_1","unstructured":"Jason Antic. 2019. DeOldify: A open-source project for colorizing old images (and video)."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2288929"},{"key":"e_1_2_1_4_1","volume-title":"COCO-Stuff: Thing and Stuff Classes in Context. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Caesar Holger","year":"2018","unstructured":"Holger Caesar, Jasper R. R. Uijlings, and Vittorio Ferrari. 2018. COCO-Stuff: Thing and Stuff Classes in Context. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766978"},{"key":"e_1_2_1_6_1","volume-title":"Deep Colorization. In IEEE International Conference on Computer Vision (ICCV).","author":"Cheng Zezhou","year":"2015","unstructured":"Zezhou Cheng, Qingxiong Yang, and Bin Sheng. 2015. Deep Colorization. In IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024190"},{"key":"e_1_2_1_8_1","volume-title":"European Conference on Computer Vision (ECCV).","author":"Cho Wonwoong","year":"2018","unstructured":"Wonwoong Cho, Hyojin Bahng, David Keetae Park, Seungjoo Yoo, Ziming Wu, Xiaojuan Ma, and Jaegul Choo. 2018. Text2Colors: Guiding Image Colorization through Text-Driven Palette Generation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_1_10_1","volume-title":"Learning Diverse Image Colorization. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Deshpande Aditya","unstructured":"Aditya Deshpande, Jiajun Lu, Mao-Chuang Yeh, Min Jin Chong, and David A. Forsyth. 2017. Learning Diverse Image Colorization. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_1_11_1","volume-title":"Learning Large-Scale Automatic Image Colorization. In IEEE International Conference on Computer Vision (ICCV).","author":"Deshpande Aditya","unstructured":"Aditya Deshpande, Jason Rock, and David A. Forsyth. 2015. Learning Large-Scale Automatic Image Colorization. In IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_2_1_12_1","volume-title":"Image Processing Using Multi-Code GAN Prior. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Gu Jinjin","year":"2020","unstructured":"Jinjin Gu, Yujun Shen, and Bolei Zhou. 2020. Image Processing Using Multi-Code GAN Prior. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_1_13_1","volume-title":"PixColor: Pixel Recursive Colorization. In British Machine Vision Conference 2017 (BMVC).","author":"Guadarrama Sergio","year":"2017","unstructured":"Sergio Guadarrama, Ryan Dahl, David Bieber, Jonathon Shlens, Mohammad Norouzi, and Kevin Murphy. 2017. PixColor: Pixel Recursive Colorization. In British Machine Vision Conference 2017 (BMVC)."},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","unstructured":"David Hasler and Sabine S\u00fcsstrunk. 2003. Measuring colorfulness in natural images. In Human Vision and Electronic Imaging VIII.","DOI":"10.1117\/12.477378"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201365"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292482"},{"key":"e_1_2_1_17_1","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS).","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925974"},{"key":"e_1_2_1_19_1","volume-title":"Eurographics Symposium on Rendering Techniques.","author":"Ironi Revital","year":"2005","unstructured":"Revital Ironi, Daniel Cohen-Or, and Dani Lischinski. 2005. Colorization by Example. In Eurographics Symposium on Rendering Techniques."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01440"},{"key":"e_1_2_1_21_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint:1511.06349 (2014)."},{"key":"e_1_2_1_22_1","volume-title":"Colorization Transformer. In International Conference on Learning Representations (ICLR).","author":"Kumar Manoj","year":"2021","unstructured":"Manoj Kumar, DirkWeissenborn, and Nal Kalchbrenner. 2021. Colorization Transformer. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_1_23_1","volume-title":"Learning Representations for Automatic Colorization. In European Conference on Computer Vision (ECCV).","author":"Larsson Gustav","year":"2016","unstructured":"Gustav Larsson, Michael Maire, and Gregory Shakhnarovich. 2016. Learning Representations for Automatic Colorization. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015780"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2732239"},{"key":"e_1_2_1_26_1","volume-title":"Seitz","author":"Luo Xuan","year":"2020","unstructured":"Xuan Luo, Yanmeng Kong, Jason Lawrence, Ricardo Martin-Brualla, and Steven M. Seitz. 2020. KeystoneDepth: History in 3D. In International Conference on 3D Vision (3DV). https:\/\/keystonedepth.cs.washington.edu"},{"key":"e_1_2_1_27_1","volume-title":"Structural Consistency and Controllability for Diverse Colorization. In European Conference on Computer Vision (ECCV).","author":"Messaoud Safa","unstructured":"Safa Messaoud, David A. Forsyth, and Alexander G. Schwing. 2018. Structural Consistency and Controllability for Diverse Colorization. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142017"},{"key":"e_1_2_1_29_1","volume-title":"Improved Techniques for Training GANs. In Annual Conference on Neural Information Processing Systems (NeurIPS).","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans, Ian J. Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved Techniques for Training GANs. In Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_2_1_30_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR).","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_1_31_1","volume-title":"Instance-Aware Image Colorization. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Su Jheng-Wei","year":"2020","unstructured":"Jheng-Wei Su, Hung-Kuo Chu, and Jia-Bin Huang. 2020. Instance-Aware Image Colorization. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_1_32_1","volume-title":"Annual Conference on Neural Information Processing Systems (NeurIPS).","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_2_1_33_1","volume-title":"ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution. In IEEE Winter Conference on Applications of Computer Vision (WACV).","author":"Vitoria Patricia","year":"2020","unstructured":"Patricia Vitoria, Lara Raad, and Coloma Ballester. 2020. ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution. In IEEE Winter Conference on Applications of Computer Vision (WACV)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566576"},{"key":"e_1_2_1_35_1","volume-title":"Towards Vivid and Diverse Image Colorization with Generative Color Prior. In IEEE International Conference on Computer Vision (ICCV).","author":"Wu Yanze","year":"2021","unstructured":"Yanze Wu, Xintao Wang, Yu Li, Honglun Zhang, Xun Zhao, and Ying Shan. 2021. Towards Vivid and Diverse Image Colorization with Generative Color Prior. In IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_2_1_36_1","volume-title":"Superpixel Segmentation With Fully Convolutional Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Yang Fengting","year":"2020","unstructured":"Fengting Yang, Qian Sun, Hailin Jin, and Zihan Zhou. 2020. Superpixel Segmentation With Fully Convolutional Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.864231"},{"key":"e_1_2_1_38_1","volume-title":"Self-Attention Generative Adversarial Networks. In International Conference on Machine Learning (ICML).","author":"Zhang Han","year":"2019","unstructured":"Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena. 2019. Self-Attention Generative Adversarial Networks. In International Conference on Machine Learning (ICML)."},{"key":"e_1_2_1_39_1","volume-title":"Colorful Image Colorization. In European Conference on Computer Vision (ECCV).","author":"Zhang Richard","unstructured":"Richard Zhang, Phillip Isola, and Alexei A. Efros. 2016. Colorful Image Colorization. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073703"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01271-4"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555432","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550454.3555432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:11Z","timestamp":1750182551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1145\/3550454.3555432"],"URL":"https:\/\/doi.org\/10.1145\/3550454.3555432","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"assertion":[{"value":"2022-11-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}