{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:34:35Z","timestamp":1785267275600,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730122","type":"print"},{"value":"9783031730139","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73013-9_24","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:51:53Z","timestamp":1732607513000},"page":"417-434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["DiffusionPen: Towards Controlling the\u00a0Style of\u00a0Handwritten Text Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9332-3188","authenticated-orcid":false,"given":"Konstantina","family":"Nikolaidou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6734-3575","authenticated-orcid":false,"given":"George","family":"Retsinas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7305-2886","authenticated-orcid":false,"given":"Giorgos","family":"Sfikas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-6574","authenticated-orcid":false,"given":"Marcus","family":"Liwicki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Alonso, E., Moysset, B., Messina, R.: Adversarial generation of handwritten text images conditioned on sequences. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 481\u2013486. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00083"},{"key":"24_CR2","unstructured":"Balaji, Y., et\u00a0al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Khan, F.S., Shah, M.: Handwriting transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1086\u20131094 (2021)","DOI":"10.1109\/ICCV48922.2021.00112"},{"key":"24_CR4","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: Textdiffuser: diffusion models as text painters. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Clark, J., Garrette, D., Turc, I., Wieting, J.: Canine: pre-training an efficient tokenization-free encoder for language representation. Trans. Assoc. Comput. Linguist. 10, 73\u201391 (2021). https:\/\/api.semanticscholar.org\/CorpusID:232185112","DOI":"10.1162\/tacl_a_00448"},{"key":"24_CR6","unstructured":"Davis, B.L., Tensmeyer, C., Price, B.L., Wigington, C., Morse, B., Jain, R.: Text and style conditioned GAN for the generation of offline-handwriting lines. In: Proceedings of the $$31^{st}$$ British Machine Vision Conference (BMVC) (2020)"},{"issue":"3","key":"24_CR7","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1016\/0047-259X(82)90077-X","volume":"12","author":"D Dowson","year":"1982","unstructured":"Dowson, D., Landau, B.: The Fr\u00e9chet distance between multivariate normal distributions. J. Multivar. Anal. 12(3), 450\u2013455 (1982)","journal-title":"J. Multivar. Anal."},{"key":"24_CR8","unstructured":"Giannone, G., Nielsen, D., Winther, O.: Few-Shot Diffusion Models. ArXiv abs\/2205.15463 (2022). https:\/\/api.semanticscholar.org\/CorpusID:249210127"},{"issue":"5","key":"24_CR9","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1109\/TPAMI.2008.137","volume":"31","author":"A Graves","year":"2008","unstructured":"Graves, A., Liwicki, M., Fern\u00e1ndez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 855\u2013868 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1007\/978-3-031-41679-8_20","volume-title":"ICDAR 2023","author":"D Gui","year":"2023","unstructured":"Gui, D., Chen, K., Ding, H., Huo, Q.: Zero-shot generation of training data with denoising diffusion probabilistic model for handwritten Chinese character recognition. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14188, pp. 348\u2013365. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_20"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"He, H., et al.: Diff-Font: diffusion model for robust one-shot font generation. Int. J. Comput. Vis. 1\u201315 (2024)","DOI":"10.1007\/s11263-024-02137-0"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Kang, L., Riba, P., Rusinol, M., Forn\u00e9s, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3122572"},{"key":"24_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-58592-1_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Kang","year":"2020","unstructured":"Kang, L., Riba, P., Wang, Y., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: GANwriting: content-conditioned generation of styled handwritten word images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 273\u2013289. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_17"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Kang, L., Rusinol, M., Forn\u00e9s, A., Riba, P., Villegas, M.: Unsupervised writer adaptation for synthetic-to-real handwritten word recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3502\u20133511 (2020)","DOI":"10.1109\/WACV45572.2020.9093392"},{"key":"24_CR17","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. In: Advances in Neural Information Processing Systems, vol. 34, pp. 21696\u201321707 (2021)"},{"key":"24_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"24_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/978-3-030-86337-1_27","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"AWC Lee","year":"2021","unstructured":"Lee, A.W.C., Chung, J., Lee, M.: GNHK: a dataset for English handwriting in the wild. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021 Part IV. LNCS, vol. 12824, pp. 399\u2013412. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_27"},{"key":"24_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017). https:\/\/api.semanticscholar.org\/CorpusID:53592270"},{"key":"24_CR21","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s100320200071","volume":"5","author":"UV Marti","year":"2002","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recogn. 5, 39\u201346 (2002)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"24_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1007\/978-3-030-86549-8_18","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"A Mattick","year":"2021","unstructured":"Mattick, A., Mayr, M., Seuret, M., Maier, A., Christlein, V.: SmartPatch: improving handwritten word imitation with patch discriminators. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 268\u2013283. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_18"},{"key":"24_CR23","unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, pp. 16784\u201316804. PMLR (2022)"},{"key":"24_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1007\/978-3-031-41679-8_22","volume-title":"ICDAR 2023","author":"K Nikolaidou","year":"2023","unstructured":"Nikolaidou, K., et al.: WordStylist: styled verbatim handwritten text generation with latent diffusion models. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14188, pp. 384\u2013401. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_22"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Pippi, V., Cascianelli, S., Cucchiara, R.: Handwritten text generation from visual archetypes. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22458\u201322467 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257766680","DOI":"10.1109\/CVPR52729.2023.02151"},{"key":"24_CR26","volume-title":"Understanding Deep Learning","author":"SJ Prince","year":"2023","unstructured":"Prince, S.J.: Understanding Deep Learning. MIT Press, Cambridge (2023)"},{"key":"24_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"24_CR28","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"24_CR29","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-031-06555-2_17","volume-title":"DAS 2022","author":"G Retsinas","year":"2022","unstructured":"Retsinas, G., Sfikas, G., Gatos, B., Nikou, C.: Best practices for a handwritten text recognition system. In: Uchida, S., Barney, E., Eglin, V. (eds.) DAS 2022. LNCS, vol. 13237, pp. 247\u2013259. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_17"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015 PArt III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"24_CR32","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018). https:\/\/api.semanticscholar.org\/CorpusID:4555207","DOI":"10.1109\/CVPR.2018.00474"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Fogel, S., Averbuch-Elor, H, Cohen, S., Mazor, S., Litman, R.: ScrabbleGAN: semi-supervised varying length handwritten text generation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4323\u20134332 (2020)","DOI":"10.1109\/CVPR42600.2020.00438"},{"key":"24_CR35","unstructured":"Sinha, A., Song, J., Meng, C., Ermon, S.: D2C: diffusion-decoding models for few-shot conditional generation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12533\u201312548 (2021)"},{"key":"24_CR36","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"24_CR37","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"24_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"4","key":"24_CR39","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Yang, Z., Peng, D., Kong, Y., Zhang, Y., Yao, C., Jin, L.: FontDiffuser: one-shot font generation via denoising diffusion with multi-scale content aggregation and style contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 6603\u20136611 (2024)","DOI":"10.1609\/aaai.v38i7.28482"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, L., Chen, X., Wang, Y., Lu, Y., Qiao, Y.: Brush your text: synthesize any scene text on images via diffusion model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 7215\u20137223 (2024)","DOI":"10.1609\/aaai.v38i7.28550"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Li, Z., Wang, T., He, M., Yao, C.: Conditional text image generation with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14235\u201314245 (2023)","DOI":"10.1109\/CVPR52729.2023.01368"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73013-9_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:33:41Z","timestamp":1732610021000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73013-9_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031730122","9783031730139"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73013-9_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}