{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:47:10Z","timestamp":1774021630050,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730660","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:40:47Z","timestamp":1753260047000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Cobra: Efficient Line Art COlorization with BRoAder References"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1642-0750","authenticated-orcid":false,"given":"Junhao","family":"Zhuang","sequence":"first","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1313-8717","authenticated-orcid":false,"given":"Lingen","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0668-1375","authenticated-orcid":false,"given":"Xuan","family":"Ju","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5583-6454","authenticated-orcid":false,"given":"Zhaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3590-6676","authenticated-orcid":false,"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_27"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_4_1","unstructured":"Yu Cao Xiangqiao Meng PY Mok Xueting Liu Tong-Yee Lee and Ping Li. 2023. AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.11137 (2023)."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Huiwen Chang Ohad Fried Yiming Liu Stephen DiVerdi and Adam Finkelstein. 2015. Palette-based photo recoloring. ACM Trans. Graph. 34 4 (2015) 139\u20131.","DOI":"10.1145\/2766978"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_21"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01842"},{"key":"e_1_3_3_2_8_1","unstructured":"Junsong Chen Jincheng Yu Chongjian Ge Lewei Yao Enze Xie Yue Wu Zhongdao Wang James Kwok Ping Luo Huchuan Lu et\u00a0al. 2023. Pixart-\u03b1 : Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.00426 (2023)."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240661"},{"key":"e_1_3_3_2_11_1","unstructured":"Ning Ding Yujia Qin Guang Yang Fuchao Wei Zonghan Yang Yusheng Su Shengding Hu Yulin Chen Chi-Min Chan Weize Chen et\u00a0al. 2022. Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.06904 (2022)."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Zhi Dou Ning Wang Baopu Li Zhihui Wang Haojie Li and Bin Liu. 2021. Dual color space guided sketch colorization. IEEE Transactions on Image Processing 30 (2021) 7292\u20137304.","DOI":"10.1109\/TIP.2021.3104190"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3145749.3149430"},{"key":"e_1_3_3_2_14_1","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit\u00a0H Bermano Gal Chechik and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.01618 (2022)."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Rinon Gal Moab Arar Yuval Atzmon Amit\u00a0H Bermano Gal Chechik and Daniel Cohen-Or. 2023. Encoder-based domain tuning for fast personalization of text-to-image models. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201313.","DOI":"10.1145\/3592133"},{"key":"e_1_3_3_2_16_1","unstructured":"Amir Hertz Ron Mokady Jay Tenenbaum Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.01626 (2022)."},{"key":"e_1_3_3_2_17_1","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. Advances in Neural Information Processing Systems (NIPS) 30 (2017)."},{"key":"e_1_3_3_2_18_1","unstructured":"Lianghua Huang Wei Wang Zhi-Fan Wu Yupeng Shi Huanzhang Dou Chen Liang Yutong Feng Yu Liu and Jingren Zhou. 2024. In-context lora for diffusion transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.23775 (2024)."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"e_1_3_3_2_20_1","unstructured":"Xuan Ju Xian Liu Xintao Wang Yuxuan Bian Ying Shan and Qiang Xu. 2024. Brushnet: A plug-and-play image inpainting model with decomposed dual-branch diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.06976 (2024)."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00915"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"crossref","unstructured":"Chengze Li Xueting Liu and Tien-Tsin Wong. 2017. Deep Extraction of Manga Structural Lines. ACM Transactions on Graphics (SIGGRAPH 2017 issue) 36 4 (July 2017) 117:1\u2013117:12.","DOI":"10.1145\/3072959.3073675"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"e_1_3_3_2_25_1","unstructured":"Zhexin Liang Zhaochen Li Shangchen Zhou Chongyi Li and Chen\u00a0Change Loy. 2024. Control Color: Multimodal Diffusion-based Interactive Image Colorization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.10855 (2024)."},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Yifan Liu Zengchang Qin Tao Wan and Zhenbo Luo. 2018. Auto-painter: Cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks. Neurocomputing 311 (2018) 78\u201387.","DOI":"10.1016\/j.neucom.2018.05.045"},{"key":"e_1_3_3_2_27_1","unstructured":"Maksim Golyadkin. 2024. Automatic colorization. https:\/\/github.com\/qweasdd\/manga-colorization-v2 [Online; accessed 4-Oct-2024]."},{"key":"e_1_3_3_2_28_1","unstructured":"Yihao Meng Hao Ouyang Hanlin Wang Qiuyu Wang Wen Wang Ka\u00a0Leong Cheng Zhiheng Liu Yujun Shen and Huamin Qu. 2024. AniDoc: Animation Creation Made Easier. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.14173 (2024)."},{"key":"e_1_3_3_2_29_1","unstructured":"Reiner Pope Sholto Douglas Aakanksha Chowdhery Jacob Devlin James Bradbury Anselm Levskaya Jonathan Heek Kefan Xiao Shivani Agrawal and Jeff Dean. 2022. Efficiently Scaling Transformer Inference. arxiv:https:\/\/arXiv.org\/abs\/2211.05102\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2211.05102"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Yingge Qu Tien-Tsin Wong and Pheng-Ann Heng. 2006. Manga colorization. ACM Transactions on Graphics (ToG) 25 3 (2006) 1214\u20131220.","DOI":"10.1145\/1141911.1142017"},{"key":"e_1_3_3_2_31_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et\u00a0al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems 35 (2022) 25278\u201325294.","DOI":"10.52202\/068431-1833"},{"key":"e_1_3_3_2_36_1","unstructured":"Chaitat Utintu Pinaki\u00a0Nath Chowdhury Aneeshan Sain Subhadeep Koley Ayan\u00a0Kumar Bhunia and Yi-Zhe Song. 2024. SketchDeco: Decorating B&W Sketches with Colour. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.18716 (2024)."},{"key":"e_1_3_3_2_37_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arxiv:https:\/\/arXiv.org\/abs\/1706.03762\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"crossref","unstructured":"Hanzhang Wang Deming Zhai Xianming Liu Junjun Jiang and Wen Gao. 2023. Unsupervised deep exemplar colorization via pyramid dual non-local attention. IEEE Transactions on Image Processing (2023).","DOI":"10.1109\/TIP.2023.3293777"},{"key":"e_1_3_3_2_39_1","unstructured":"Qixun Wang Xu Bai Haofan Wang Zekui Qin Anthony Chen Huaxia Li Xu Tang and Yao Hu. 2024. Instantid: Zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.07519 (2024)."},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_16"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_2_42_1","unstructured":"Shuchen Weng Peixuan Zhang Yu Li Si Li Boxin Shi et\u00a0al. 2024. L-cad: Language-based colorization with any-level descriptions using diffusion priors. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_43_1","unstructured":"Wikipedia contributors. 2024. Peak signal-to-noise ratio \u2014 Wikipedia The Free Encyclopedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Peak_signal-to-noise_ratio&oldid=1210897995 [Online; accessed 4-March-2024]."},{"key":"e_1_3_3_2_44_1","unstructured":"Shukai Wu Xiao Yan Weiming Liu Shuchang Xu and Sanyuan Zhang. 2023a. Self-driven dual-path learning for reference-based line art colorization under limited data. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612182"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00882"},{"key":"e_1_3_3_2_47_1","unstructured":"Xiaoyu Xiang Ding Liu Yiheng\u00a0Zhu Xiao\u00a0Yang and Xiaohui Shen. 2021. Anime2Sketch: A Sketch Extractor for Anime Arts with Deep Networks. https:\/\/github.com\/Mukosame\/Anime2Sketch."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13659"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Minshan Xie Chengze Li Xueting Liu and Tien-Tsin Wong. 2020. Manga filling style conversion with screentone variational autoencoder. ACM Transactions on Graphics (TOG) 39 6 (2020) 1\u201315.","DOI":"10.1145\/3414685.3417873"},{"key":"e_1_3_3_2_50_1","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.06721 (2023)."},{"key":"e_1_3_3_2_51_1","unstructured":"Gokul Yenduri Ramalingam M Chemmalar\u00a0Selvi G Supriya Y Gautam Srivastava Praveen Kumar\u00a0Reddy Maddikunta Deepti\u00a0Raj G Rutvij\u00a0H Jhaveri Prabadevi B Weizheng Wang Athanasios\u00a0V. Vasilakos and Thippa\u00a0Reddy Gadekallu. 2023. Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies Potential Applications Emerging Challenges and Future Directions. arxiv:https:\/\/arXiv.org\/abs\/2305.10435\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.10435"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00183"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618180"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00976"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Chengze Li Tien-Tsin Wong Yi Ji and Chunping Liu. 2018. Two-stage sketch colorization. ACM Transactions on Graphics (TOG) 37 6 (2018) 1\u201314.","DOI":"10.1145\/3272127.3275090"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_57_1","unstructured":"Junhao Zhuang Xuan Ju Zhaoyang Zhang Yong Liu Shiyi Zhang Chun Yuan and Ying Shan. 2024. ColorFlow: Retrieval-Augmented Image Sequence Colorization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.11815 (2024)."},{"key":"e_1_3_3_2_58_1","unstructured":"Junhao Zhuang Yanhong Zeng Wenran Liu Chun Yuan and Kai Chen. 2023. A task is worth one word: Learning with task prompts for high-quality versatile image inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.03594 (2023)."},{"key":"e_1_3_3_2_59_1","unstructured":"Chengyi Zou Shuai Wan Marc\u00a0Gorriz Blanch Luka Murn Marta Mrak Juil Sock Fei Yang and Luis Herranz. 2024. Lightweight Deep Exemplar Colorization via Semantic Attention-Guided Laplacian Pyramid. IEEE Transactions on Visualization and Computer Graphics (2024)."}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:52:26Z","timestamp":1774018346000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730660"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":58,"alternative-id":["10.1145\/3721238.3730660","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730660","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}