{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T15:11:23Z","timestamp":1769181083512,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819555666","type":"print"},{"value":"9789819555673","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5567-3_34","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:48Z","timestamp":1769116428000},"page":"494-507","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DiffCTE: Consistent Visual Text Editing with\u00a0High Style Fidelity via\u00a0Diffusion Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3789-9705","authenticated-orcid":false,"given":"Haoyu","family":"Cao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9863-7689","authenticated-orcid":false,"given":"Anqi","family":"Gou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1895-7799","authenticated-orcid":false,"given":"Haobin","family":"Cao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"issue":"9","key":"34_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3557999","volume":"55","author":"J Cao","year":"2023","unstructured":"Cao, J., Lam, K.Y., Lee, L.H., Liu, X., Hui, P., Su, X.: Mobile augmented reality: user interfaces, frameworks, and intelligence. ACM Comput. Surv. 55(9), 1\u201336 (2023)","journal-title":"ACM Comput. Surv."},{"key":"34_CR2","unstructured":"Huang, Q., Fu, B., Zhang, A., Qiao, Y.: GenText: unsupervised artistic text generation via decoupled font and texture manipulation. arXiv preprint arXiv:2207.09649 (2022)"},{"key":"34_CR3","unstructured":"Shi, Y., Ding, H., Chen, K., Huo, Q.: APRNet: attention-based pixel-wise rendering network for photo-realistic text image generation. arXiv preprint arXiv:2203.07705 (2022)"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Wu, L., et al.: Editing text in the wild. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3343031.3350929"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Zhan, F., Zhu, H., Lu, S.: Spatial fusion GAN for image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3653\u20133662 (2019)","DOI":"10.1109\/CVPR.2019.00377"},{"key":"34_CR6","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1007\/s11263-020-01411-1","volume":"129","author":"C Luo","year":"2021","unstructured":"Luo, C., Lin, Q., Liu, Y., Jin, L., Shen, C.: Separating content from style using adversarial learning for recognizing text in the wild. Int. J. Comput. Vis. 129, 960\u2013976 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Roy, P., Bhattacharya, S., Ghosh, S., Pal, U.: STEFANN: scene text editor using font adaptive neural network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13228\u201313237 (2020)","DOI":"10.1109\/CVPR42600.2020.01324"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Qu, Y., Tan, Q., Xie, H., Xu, J., Wang, Y., Zhang, Y.: Exploring stroke-level modifications for scene text editing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2119\u20132127 (2023)","DOI":"10.1609\/aaai.v37i2.25305"},{"key":"34_CR9","unstructured":"Su, T., Yang, F., Zhou, X., Di, D., Wang, Z., Li, S.: Scene style text editing. arXiv preprint arXiv:2304.10097 (2023)"},{"key":"34_CR10","unstructured":"Ji, J., et al.: Improving diffusion models for scene text editing with dual encoders. arXiv preprint arXiv:2304.05568 (2023)"},{"key":"34_CR11","unstructured":"Chen, H., et al.: DiffUTE: universal text editing diffusion model. In: Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"34_CR12","unstructured":"Tuo, Y., Xiang, W., He, J.Y., Geng, Y., Xie, X.: AnyText: multilingual visual text generation and editing. In: ICLR (2024)"},{"key":"34_CR13","unstructured":"Tuo, Y., Geng, Y., Bo, L.: AnyText2: visual text generation and editing with customizable attributes. arXiv preprint arXiv:2411.15245 (2024)"},{"key":"34_CR14","doi-asserted-by":"publisher","unstructured":"Liu, Z., et al.: Glyph-byt5: A customized text encoder for accurate visual text rendering. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision. LNCS, pp. 361\u2013377. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73226-3_21","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, W., Xu, H., Jin, C.: DreamText: high fidelity scene text synthesis. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 28555\u201328563 (2025)","DOI":"10.1109\/CVPR52734.2025.02659"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: ARTIST: improving the generation of text-rich images with disentangled diffusion models and large language models. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1268\u20131278. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00131"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Ma, J., Deng, Y., Chen, C., Du, N., Lu, H., Yang, Z.: GlyphDraw2: automatic generation of complex glyph posters with diffusion models and large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 5955\u20135963 (2025)","DOI":"10.1609\/aaai.v39i6.32636"},{"key":"34_CR18","doi-asserted-by":"publisher","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision. LNCS, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Kong, Y., et al.: Look closer to supervise better: one-shot font generation via component-based discriminator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13482\u201313491 (2022)","DOI":"10.1109\/CVPR52688.2022.01312"},{"key":"34_CR20","unstructured":"Brack, M., Friedrich, F., Hintersdorf, D., Struppek, L., Schramowski, P., Kersting, K.: SEGA: instructing diffusion using semantic dimensions. arXiv preprint arXiv:2301.12247 (2023)"},{"key":"34_CR21","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR22","unstructured":"Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Guiding text-to-image diffusion model towards grounded generation. arXiv preprint arXiv:2301.05221 (2023)"},{"key":"34_CR23","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":"34_CR24","unstructured":"Li, H.: CDLA: a Chinese document layout analysis (CDLA) dataset (2021)"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: XFUND: a benchmark dataset for multilingual visually rich form understanding. In: Findings of the Association for Computational Linguistics, ACL 2022, pp. 3214\u20133224 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.253"},{"key":"34_CR26","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Guo, H., Qin, X., Liu, J., Han, J., Liu, J., Ding, E.: EATEN: entity-aware attention for single shot visual text extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 254\u2013259. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00049"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et\u00a0al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Chng, C.K., et\u00a0al.: ICDAR2019 robust reading challenge on arbitrary-shaped text-RRC-ArT. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1571\u20131576. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Gomez, R., et al.: ICDAR2017 robust reading challenge on COCO-text. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 1435\u20131443. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.234"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: TextOCR: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8802\u20138812 (2021)","DOI":"10.1109\/CVPR46437.2021.00869"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5567-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:55Z","timestamp":1769116435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5567-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819555666","9789819555673"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5567-3_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}