{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:46Z","timestamp":1777865326054,"version":"3.51.4"},"reference-count":104,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01411","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15205-15217","source":"Crossref","is-referenced-by-count":4,"title":["Magiccolor: Multi-Instance Sketch Colorization"],"prefix":"10.1109","author":[{"family":"Zhang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology,Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Ma","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14396"},{"key":"ref6","article-title":"AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models","author":"Cao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00351"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01113"},{"key":"ref9","article-title":"Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024190"},{"key":"ref12","first-page":"9011","article-title":"CATs: Cost Aggregation Transformers for Visual Correspondence","volume":"34","author":"Cho","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3104190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32304"},{"key":"ref15","article-title":"An Image is Worth One Word: Personalizing Text-ToImage Generation Using Textual Inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Generative Adversarial Nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.112"},{"key":"ref18","article-title":"Prompt-To-Prompt Image Editing with Cross Attention Control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"8153","article-title":"Animate Anyone: Consistent and Controllable Image-To-Video Synthesis for Character Animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2981994"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555471"},{"issue":"4","key":"ref22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925974","article-title":"Let There Be Color! Joint End-To-End Learning of Global and Local Image Priors for Automatic Image Colorization With Simultaneous Classification","volume":"35","author":"Iizuka","year":"2016","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_2"},{"key":"ref24","article-title":"COTRACKER3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00915"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00850"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00584"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01295"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00387"},{"key":"ref33","article-title":"SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"OmniBooth: Learning Latent Control for Image Synthesis with Multi-Modal Instruction","volume-title":"arXiv preprint","author":"Li","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02209"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_35"},{"key":"ref37","article-title":"MagicMix: Semantic Mixing with Diffusion Models","author":"Liew","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0228-6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.045"},{"key":"ref42","article-title":"Cones: Concept Neurons in Diffusion Models for Customized Generation","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"57500","article-title":"Cones 2: Customizable Image Synthesis With Multiple Subjects","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Liu","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00532"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref46","article-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Lyu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548257"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00909"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref50","article-title":"Follow-Your-Click: Opendomain Regional Image Animation via Short Prompts","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3306214.3338560"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01695"},{"key":"ref54","article-title":"DINOV2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Locate, Assign, Refine:Taming Customized Image Inpainting with Text-Subject Guidance","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Sakuga-42M Dataset: Scaling Up Cartoon Research","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01311"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142017"},{"key":"ref59","first-page":"8748","article-title":"Learning Transferable Visual Models from Natural Language Supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00661"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.723"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00652"},{"key":"ref67","article-title":"Denoising Diffusion Implicit Models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00799"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01063"},{"key":"ref72","article-title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","volume-title":"arXiv preprint","author":"Sushko","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3658237"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref76","article-title":"SketchDeco: Decorating B&W Sketches with Colour","author":"Utintu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3728459"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/VR59515.2025.00067"},{"key":"ref79","article-title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"Taming Rectified Flow for Inversion and Editing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2003.819861"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612182"},{"key":"ref85","article-title":"DreamInpainter: Text-Guided Subject-Driven Image Inpainting With Diffusion Models","author":"Xie","year":"2023","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref87","article-title":"Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose Control","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14791"},{"key":"ref89","article-title":"Colorizediffusion: Adjustable Sketch Colorization With Reference Image and Text","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref91","article-title":"IdentityPreserving Text-to-Video Generation by Frequency Decomposition","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3558507"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618180"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00824"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275090"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00392"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref101","article-title":"Color2Embed: Fast Exemplar-Based Image Colorization Using Color Embeddings","author":"Zhao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01271-4"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33187"},{"key":"ref104","article-title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11449034.pdf?arnumber=11449034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:48Z","timestamp":1777529808000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":104,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01411","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}