{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:14:15Z","timestamp":1775132055871,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2023JJ50095"],"award-info":[{"award-number":["2023JJ50095"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00530-025-02125-5","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T03:42:59Z","timestamp":1770090179000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Edge-driven for image generation from sketches"],"prefix":"10.1007","volume":"32","author":[{"given":"Yue","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-huang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin-wang","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"2125_CR1","doi-asserted-by":"crossref","unstructured":"Olszewski, K., Ceylan, D., Xing, J., Echevarria, J., Chen, Z., Chen, W., Li, H.: Intuitive, interactive beard and hair synthesis with generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7446\u20137456 (2020)","DOI":"10.1109\/CVPR42600.2020.00747"},{"key":"2125_CR2","doi-asserted-by":"crossref","unstructured":"K\u00fct\u00fck, A., Sezgin, T.M.: Class-agnostic visio-temporal scene sketch semantic segmentation. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV), pp. 8433\u20138442 (2025)","DOI":"10.1109\/WACV61041.2025.00818"},{"key":"2125_CR3","doi-asserted-by":"crossref","unstructured":"Yan, D., Yuan, L., Wu, E., Nishioka, Y., Fujishiro, I., Saito, S.: Colorizediffusion: Improving reference-based sketch colorization with latent diffusion model. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV), pp. 5092\u20135102 (2025)","DOI":"10.1109\/WACV61041.2025.00498"},{"key":"2125_CR4","doi-asserted-by":"crossref","unstructured":"Tripathi, A., Mishra, A., Chakraborty, A.: Query-guided attention in vision transformers for localizing objects using a single sketch. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1083\u20131092 (2024)","DOI":"10.1109\/WACV57701.2024.00112"},{"key":"2125_CR5","doi-asserted-by":"crossref","unstructured":"Koley, S., Bhunia, A.K., Sekhri, D., Sain, A., Chowdhury, P.N., Xiang, T., Song, Y.-Z.: It\u2019s all about your sketch: democratising sketch control in diffusion models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00688"},{"key":"2125_CR6","doi-asserted-by":"crossref","unstructured":"Koley, S., Bhunia, A.K., Sain, A., Chowdhury, P.N., Xiang, T., Song, Y.-Z.: How to handle sketch-abstraction in sketch-based image retrieval? In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01595"},{"key":"2125_CR7","doi-asserted-by":"crossref","unstructured":"Koley, S., Bhunia, A.K., Sain, A., Chowdhury, P.N., Xiang, T., Song, Y.-Z.: Text-to-image diffusion models are great sketch-photo matchmakers. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01592"},{"key":"2125_CR8","doi-asserted-by":"crossref","unstructured":"Koley, S., Bhunia, A.K., Sain, A., Chowdhury, P.N., Xiang, T., Song, Y.-Z.: You\u2019ll never walk alone: a sketch and text duet for fine-grained image retrieval. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01562"},{"key":"2125_CR9","doi-asserted-by":"crossref","unstructured":"An, Z., Yu, J., Liu, R., Wang, C., Yu, Q.: Sketchinverter: multi-class sketch-based image generation via gan inversion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4319\u20134329 (2023)","DOI":"10.1109\/WACV56688.2023.00430"},{"key":"2125_CR10","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Chien, C.-H., Fabbri, R., Kimia, B.: 3d edge sketch from multiview images. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV), pp. 3196\u20133205 (2025)","DOI":"10.1109\/WACV61041.2025.00316"},{"issue":"7","key":"2125_CR11","doi-asserted-by":"publisher","first-page":"3250","DOI":"10.1109\/TVCG.2020.2968433","volume":"27","author":"Y Shen","year":"2020","unstructured":"Shen, Y., Zhang, C., Fu, H., Zhou, K., Zheng, Y.: Deepsketchhair: deep sketch-based 3d hair modeling. IEEE Trans. Visual Comput. Graphics 27(7), 3250\u20133263 (2020)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"2125_CR12","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"2125_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"2125_CR14","doi-asserted-by":"crossref","unstructured":"Chen, W., Hays, J.: Sketchygan: towards diverse and realistic sketch to image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9416\u20139425 (2018)","DOI":"10.1109\/CVPR.2018.00981"},{"key":"2125_CR15","unstructured":"Chen, S.-Y., Su, W., Gao, L., Xia, S., Fu, H.: Deep generation of face images from sketches. arXiv preprint arXiv:2006.01047 (2020)"},{"key":"2125_CR16","doi-asserted-by":"crossref","unstructured":"Gao, C., Liu, Q., Xu, Q., Wang, L., Liu, J., Zou, C.: Sketchycoco: image generation from freehand scene sketches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5174\u20135183 (2020)","DOI":"10.1109\/CVPR42600.2020.00522"},{"key":"2125_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, X., Yang, B., Chen, Z., Cheng, Z., Zha, Z.-J.: Deepfacepencil: creating face images from freehand sketches. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 991\u2013999 (2020)","DOI":"10.1145\/3394171.3413684"},{"key":"2125_CR18","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. Advances in neural information processing systems 27 (2014)"},{"issue":"5","key":"2125_CR19","first-page":"1","volume":"28","author":"T Chen","year":"2009","unstructured":"Chen, T., Cheng, M.-M., Tan, P., Shamir, A., Hu, S.-M.: Sketch2photo: internet image montage. ACM Trans. Graph. 28(5), 1\u201310 (2009)","journal-title":"ACM Trans. Graph."},{"issue":"6","key":"2125_CR20","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MCG.2011.67","volume":"31","author":"M Eitz","year":"2011","unstructured":"Eitz, M., Richter, R., Hildebrand, K., Boubekeur, T., Alexa, M.: Photosketcher: interactive sketch-based image synthesis. IEEE Comput. Graphics Appl. 31(6), 56\u201366 (2011)","journal-title":"IEEE Comput. Graphics Appl."},{"key":"2125_CR21","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Chowdhury, P.N., Yang, Y., Hospedales, T.M., Xiang, T., Song, Y.-Z.: Vectorization and rasterization: self-supervised learning for sketch and handwriting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5672\u20135681 (2021)","DOI":"10.1109\/CVPR46437.2021.00562"},{"key":"2125_CR22","doi-asserted-by":"crossref","unstructured":"Sain, A., Bhunia, A.K., Chowdhury, P.N., Koley, S., Xiang, T., Song, Y.-Z.: Clip for all things zero-shot sketch-based image retrieval, fine-grained or not. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2765\u20132775 (2023)","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"2125_CR23","doi-asserted-by":"crossref","unstructured":"Lin, F., Li, M., Li, D., Hospedales, T., Song, Y.-Z., Qi, Y.: Zero-shot everything sketch-based image retrieval, and in explainable style. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23349\u201323358 (2023)","DOI":"10.1109\/CVPR52729.2023.02236"},{"key":"2125_CR24","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.-Y., Wang, T.-C., Zhu, J.-Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"2125_CR25","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-assisted intervention\u2014MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234\u2013241 (2015). Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2125_CR26","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.ins.2022.08.005","volume":"610","author":"Y Huang","year":"2022","unstructured":"Huang, Y., Bian, S., Li, H., Wang, C., Li, K.: Ds-unet: a dual streams unet for refined image forgery localization. Inf. Sci. 610, 73\u201389 (2022)","journal-title":"Inf. Sci."},{"key":"2125_CR27","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Jiang, A., Liu, C., Wang, M.: Single image colorization via modified cyclegan. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 3247\u20133251 (2019). IEEE","DOI":"10.1109\/ICIP.2019.8803677"},{"key":"2125_CR28","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Huang, W., Scott, M.R., Davis, L.S.: Finet: compatible and diverse fashion image inpainting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4481\u20134491 (2019)","DOI":"10.1109\/ICCV.2019.00458"},{"key":"2125_CR29","doi-asserted-by":"crossref","unstructured":"Qu, Y., Chen, Y., Huang, J., Xie, Y.: Enhanced pix2pix dehazing network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8160\u20138168 (2019)","DOI":"10.1109\/CVPR.2019.00835"},{"key":"2125_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, X., Wu, F., Zha, Z.-J.: Linestofacephoto: face photo generation from lines with conditional self-attention generative adversarial networks. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2323\u20132331 (2019)","DOI":"10.1145\/3343031.3350854"},{"key":"2125_CR31","doi-asserted-by":"crossref","unstructured":"Lu, Y., Wu, S., Tai, Y.-W., Tang, C.-K.: Image generation from sketch constraint using contextual gan. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 205\u2013220 (2018)","DOI":"10.1007\/978-3-030-01270-0_13"},{"key":"2125_CR32","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Zhang, R., Dokania, P.K., Wang, O., Efros, A.A., Torr, P.H., Shechtman, E.: Interactive sketch and fill: multiclass sketch-to-image translation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1171\u20131180 (2019)","DOI":"10.1109\/ICCV.2019.00126"},{"key":"2125_CR33","doi-asserted-by":"crossref","unstructured":"Xiang, X., Liu, D., Yang, X., Zhu, Y., Shen, X., Allebach, J.P.: Adversarial open domain adaptation for sketch-to-photo synthesis. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1434\u20131444 (2022)","DOI":"10.1109\/WACV51458.2022.00102"},{"key":"2125_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109461","volume":"139","author":"X Soria","year":"2023","unstructured":"Soria, X., Sappa, A., Humanante, P., Akbarinia, A.: Dense extreme inception network for edge detection. Pattern Recogn. 139, 109461 (2023)","journal-title":"Pattern Recogn."},{"key":"2125_CR35","doi-asserted-by":"crossref","unstructured":"Yu, Q., Liu, F., Song, Y.-Z., Xiang, T., Hospedales, T.M., Loy, C.-C.: Sketch me that shoe. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 799\u2013807 (2016)","DOI":"10.1109\/CVPR.2016.93"},{"key":"2125_CR36","doi-asserted-by":"crossref","unstructured":"Song, J., Yu, Q., Song, Y.-Z., Xiang, T., Hospedales, T.M.: Deep spatial-semantic attention for fine-grained sketch-based image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5551\u20135560 (2017)","DOI":"10.1109\/ICCV.2017.592"},{"key":"2125_CR37","doi-asserted-by":"crossref","unstructured":"Liu, R., Yu, Q., Yu, S.X.: Unsupervised sketch to photo synthesis. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16, pp. 36\u201352 (2020). Springer","DOI":"10.1007\/978-3-030-58580-8_3"},{"key":"2125_CR38","doi-asserted-by":"crossref","unstructured":"Richardson, E., Alaluf, Y., Patashnik, O., Nitzan, Y., Azar, Y., Shapiro, S., Cohen-Or, D.: Encoding in style: a stylegan encoder for image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2287\u20132296 (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"2125_CR39","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 172\u2013189 (2018)","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"2125_CR40","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., Shan, Y., Qie, X.: T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"2125_CR41","doi-asserted-by":"crossref","unstructured":"Bashkirova, D., Lezama, J., Sohn, K., Saenko, K., Essa, I.: Masksketch: unpaired structure-guided masked image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1879\u20131889 (2023)","DOI":"10.1109\/CVPR52729.2023.00187"},{"key":"2125_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding Conditional Control to Text-to-Image Diffusion Models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2125_CR43","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, pp. 10506\u201310518 (2019)"},{"key":"2125_CR44","doi-asserted-by":"crossref","unstructured":"Ham, C., Tarres, G.C., Bui, T., Hays, J., Lin, Z., Collomosse, J.: Cogs: controllable generation and search from sketch and style. European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19787-1_36"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02125-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02125-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02125-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:37:12Z","timestamp":1775129832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02125-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2125"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02125-5","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"assertion":[{"value":"8 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"107"}}