{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:02:09Z","timestamp":1780020129606,"version":"3.53.1"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116222","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:52:19Z","timestamp":1779205939000},"page":"116222","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Text image inpainting via Text-Referenced Residual Diffusion Model in latent space"],"prefix":"10.1016","volume":"346","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6159-5349","authenticated-orcid":false,"given":"Rongji","family":"Ke","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1135-9807","authenticated-orcid":false,"given":"Degang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6693-0161","authenticated-orcid":false,"given":"Hengyou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.knosys.2026.116222_b1","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","article-title":"Scene text detection and recognition: The deep learning era","volume":"129","author":"Long","year":"2021","journal-title":"Int. J. Comput. Vis."},{"issue":"7","key":"10.1016\/j.knosys.2026.116222_b2","doi-asserted-by":"crossref","first-page":"9122","DOI":"10.1109\/TPAMI.2023.3239736","article-title":"TextStyleBrush: Transfer of text aesthetics from a single example","volume":"45","author":"Krishnan","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116222_b3","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2119","article-title":"Exploring stroke-level modifications for scene text editing","author":"Qu","year":"2023"},{"issue":"10","key":"10.1016\/j.knosys.2026.116222_b4","doi-asserted-by":"crossref","first-page":"6472","DOI":"10.1109\/TPAMI.2021.3087619","article-title":"SynSig2Vec: Forgery-free learning of dynamic signature representations by sigma lognormal-based synthesis and 1D CNN","volume":"44","author":"Lai","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116222_b5","doi-asserted-by":"crossref","unstructured":"L. Haritha, C.A. Prajith, Image Inpainting Using Deep Learning Techniques: A Review, in: Proceedings of International Conference on Control, Communication and Computing, 2023, pp. 1\u20136.","DOI":"10.1109\/ICCC57789.2023.10165271"},{"key":"10.1016\/j.knosys.2026.116222_b6","doi-asserted-by":"crossref","first-page":"138441","DOI":"10.1109\/ACCESS.2024.3461782","article-title":"Review of deep learning-based image inpainting techniques","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116222_b7","unstructured":"G. Zhang, J. Ji, Y. Zhang, M. Yu, T.S. Jaakkola, S. Chang, Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models, in: Proceedings of International Conference on Machine Learning, Vol. 202, 2023, pp. 41164\u201341193."},{"key":"10.1016\/j.knosys.2026.116222_b8","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7775","article-title":"Text image inpainting via global structure-guided diffusion models","author":"Zhu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116222_b9","doi-asserted-by":"crossref","unstructured":"R. Shah, A. Gautam, S.K. Singh, Overview of Image Inpainting Techniques: A Survey, in: Proceedings of IEEE Region 10 Symposium, 2022, pp. 1\u20136.","DOI":"10.1109\/TENSYMP54529.2022.9864513"},{"key":"10.1016\/j.knosys.2026.116222_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109046","article-title":"Deep learning for image inpainting: A survey","volume":"134","author":"Xiang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116222_b11","doi-asserted-by":"crossref","unstructured":"D. Pathak, P. Kr\u00e4henb\u00fchl, J. Donahue, T. Darrell, A.A. Efros, Context Encoders: Feature Learning by Inpainting, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2536\u20132544.","DOI":"10.1109\/CVPR.2016.278"},{"issue":"4","key":"10.1016\/j.knosys.2026.116222_b12","doi-asserted-by":"crossref","DOI":"10.1145\/3072959.3073659","article-title":"Globally and locally consistent image completion","volume":"36","author":"Iizuka","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.knosys.2026.116222_b13","doi-asserted-by":"crossref","unstructured":"C. Yang, X. Lu, Z. Lin, E. Shechtman, O. Wang, H. Li, High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4076\u20134084.","DOI":"10.1109\/CVPR.2017.434"},{"key":"10.1016\/j.knosys.2026.116222_b14","doi-asserted-by":"crossref","unstructured":"G. Liu, F.A. Reda, K.J. Shih, T.-C. Wang, A. Tao, B. Catanzaro, Image Inpainting for Irregular Holes Using Partial Convolutions, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 89\u2013105.","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"10.1016\/j.knosys.2026.116222_b15","doi-asserted-by":"crossref","unstructured":"J. Yu, Z. Lin, J. Yang, X. Shen, X. Lu, T. Huang, Free-Form Image Inpainting With Gated Convolution, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4470\u20134479.","DOI":"10.1109\/ICCV.2019.00457"},{"key":"10.1016\/j.knosys.2026.116222_b16","doi-asserted-by":"crossref","first-page":"1784","DOI":"10.1109\/TIP.2020.3048629","article-title":"Dynamic selection network for image inpainting","volume":"30","author":"Wang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116222_b17","doi-asserted-by":"crossref","first-page":"4855","DOI":"10.1109\/TIP.2021.3076310","article-title":"Image inpainting by end-to-end cascaded refinement with mask awareness","volume":"30","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116222_b18","doi-asserted-by":"crossref","unstructured":"C. Xie, S. Liu, C. Li, M.-M. Cheng, W. Zuo, X. Liu, S. Wen, E. Ding, Image Inpainting With Learnable Bidirectional Attention Maps, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 8857\u20138866.","DOI":"10.1109\/ICCV.2019.00895"},{"key":"10.1016\/j.knosys.2026.116222_b19","doi-asserted-by":"crossref","unstructured":"J. Yu, Z.L. Lin, J. Yang, X. Shen, X. Lu, T.S. Huang, Generative Image Inpainting with Contextual Attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 5505\u20135514.","DOI":"10.1109\/CVPR.2018.00577"},{"key":"10.1016\/j.knosys.2026.116222_b20","doi-asserted-by":"crossref","unstructured":"W. Li, Z. Lin, K. Zhou, L. Qi, Y. Wang, J. Jia, MAT: Mask-Aware Transformer for Large Hole Image Inpainting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10748\u201310758.","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"10.1016\/j.knosys.2026.116222_b21","doi-asserted-by":"crossref","unstructured":"P. Shamsolmoali, M. Zareapoor, E. Granger, TransInpaint: Transformer-based Image Inpainting with Context Adaptation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2023, pp. 849\u2013858.","DOI":"10.1109\/ICCVW60793.2023.00092"},{"key":"10.1016\/j.knosys.2026.116222_b22","doi-asserted-by":"crossref","unstructured":"P. Raha, B. Chanda, Restoration of Historical Document Images Using Convolutional Neural Networks, in: Proceedings of IEEE Region 10 Symposium, 2019, pp. 56\u201361.","DOI":"10.1109\/TENSYMP46218.2019.8971112"},{"issue":"7900","key":"10.1016\/j.knosys.2026.116222_b23","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1038\/s41586-022-04448-z","article-title":"Restoring and attributing ancient texts using deep neural networks","volume":"603","author":"Assael","year":"2022","journal-title":"Nature"},{"key":"10.1016\/j.knosys.2026.116222_b24","series-title":"Proceedings of International Conference on Document Analysis and Recognition","first-page":"253","article-title":"Reconstruction of broken writing strokes in greek papyri","volume":"vol. 14193","author":"Amin","year":"2023"},{"key":"10.1016\/j.knosys.2026.116222_b25","series-title":"Proceedings of the International Conference on Pattern Recognition","first-page":"3900","article-title":"Frank-Wolfe-based multi-task learning for historical document restoration","author":"Ech-Cherif","year":"2022"},{"key":"10.1016\/j.knosys.2026.116222_b26","series-title":"Digital Techniques for Heritage Presentation and Preservation","article-title":"Text extraction and restoration of old handwritten documents","author":"Wadhwani","year":"2021"},{"key":"10.1016\/j.knosys.2026.116222_b27","series-title":"Proceedings of International Conference on Document Analysis and Recognition","first-page":"420","article-title":"A character attention generative adversarial network for degraded historical document restoration","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.knosys.2026.116222_b28","series-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5120","article-title":"Image inpainting with external-internal learning and monochromic bottleneck","author":"Wang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116222_b29","doi-asserted-by":"crossref","first-page":"5166","DOI":"10.1109\/TMM.2022.3189245","article-title":"TSINIT: A two-stage inpainting network for incomplete text","volume":"25","author":"Sun","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116222_b30","series-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10674","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.knosys.2026.116222_b31","doi-asserted-by":"crossref","unstructured":"O. Avrahami, D. Lischinski, O. Fried, Blended Diffusion for Text-driven Editing of Natural Images, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18187\u201318197.","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"10.1016\/j.knosys.2026.116222_b32","unstructured":"G. Couairon, J. Verbeek, H. Schwenk, M. Cord, DiffEdit: Diffusion-based semantic image editing with mask guidance, in: Proceedings of the International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.knosys.2026.116222_b33","doi-asserted-by":"crossref","unstructured":"T. Brooks, A. Holynski, A.A. Efros, InstructPix2Pix: Learning to Follow Image Editing Instructions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18392\u201318402.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"10.1016\/j.knosys.2026.116222_b34","unstructured":"A. Hertz, R. Mokady, J. Tenenbaum, K. Aberman, Y. Pritch, D. Cohen-Or, Prompt-to-Prompt Image Editing with Cross-Attention Control, in: Proceedings of the International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.knosys.2026.116222_b35","doi-asserted-by":"crossref","unstructured":"O. Bar-Tal, D. Ofri-Amar, R. Fridman, Y. Kasten, T. Dekel, Text2LIVE: Text-Driven Layered Image and Video Editing, in: S. Avidan, G.J. Brostow, M. Ciss\u00e9, G.M. Farinella, T. Hassner (Eds.), Proceedings of the European Conference on Computer Vision, 2022, pp. 707\u2013723.","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"10.1016\/j.knosys.2026.116222_b36","series-title":"EMNIST: an extension of MNIST to handwritten letters","author":"Cohen","year":"2017"},{"key":"10.1016\/j.knosys.2026.116222_b37","series-title":"Proceedings of International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","volume":"Vol. 162","author":"Li","year":"2022"},{"key":"10.1016\/j.knosys.2026.116222_b38","series-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11451","article-title":"RePaint: Inpainting using denoising diffusion probabilistic models","author":"Lugmayr","year":"2022"},{"key":"10.1016\/j.knosys.2026.116222_b39","series-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9935","article-title":"Generative diffusion prior for unified image restoration and enhancement","author":"Fei","year":"2023"},{"key":"10.1016\/j.knosys.2026.116222_b40","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021"},{"key":"10.1016\/j.knosys.2026.116222_b41","unstructured":"J. Ho, A. Jain, P. Abbeel, Denoising Diffusion Probabilistic Models, in: H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, H. Lin (Eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems, 2020."},{"key":"10.1016\/j.knosys.2026.116222_b42","series-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","first-page":"13049","article-title":"DiffIR: Efficient diffusion model for image restoration","author":"Xia","year":"2023"},{"key":"10.1016\/j.knosys.2026.116222_b43","unstructured":"M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, S. Hochreiter, GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium, in: Proceedings of the International Conference on Neural Information Processing Systems, 2017, pp. 6629\u20136640."},{"key":"10.1016\/j.knosys.2026.116222_b44","doi-asserted-by":"crossref","unstructured":"R. Zhang, P. Isola, A.A. Efros, E. Shechtman, O. Wang, The Unreasonable Effectiveness of Deep Features as a Perceptual Metric, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"4","key":"10.1016\/j.knosys.2026.116222_b45","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1007\/s11263-020-01419-7","article-title":"Comparison of full-reference image quality models for optimization of image processing systems","volume":"129","author":"Ding","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2026.116222_b46","series-title":"Proceedings of AAAI Conference on Artificial Intelligence","first-page":"13094","article-title":"TrOCR: Transformer-based optical character recognition with pre-trained models","author":"Li","year":"2023"},{"issue":"11","key":"10.1016\/j.knosys.2026.116222_b47","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","article-title":"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition","volume":"39","author":"Shi","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"10.1016\/j.knosys.2026.116222_b48","doi-asserted-by":"crossref","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","article-title":"ASTER: an attentional scene text recognizer with flexible rectification","volume":"41","author":"Shi","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116222_b49","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","article-title":"MORAN: A Multi-Object Rectified Attention Network for scene text recognition","volume":"90","author":"Luo","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116222_b50","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22428","article-title":"SmartBrush: Text and shape guided object inpainting with diffusion model","author":"Xie","year":"2023"},{"key":"10.1016\/j.knosys.2026.116222_b51","doi-asserted-by":"crossref","first-page":"6332","DOI":"10.1109\/TIP.2023.3298560","article-title":"Context adaptive network for image inpainting","volume":"32","author":"Deng","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116222_b52","series-title":"Proceedings of IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"4984","article-title":"GraphFill: Deep image inpainting using graphs","author":"Verma","year":"2024"},{"key":"10.1016\/j.knosys.2026.116222_b53","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Image inpainting via tractable steering of diffusion models","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116222_b54","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129749","article-title":"Transref: Multi-scale reference embedding transformer for reference-guided image inpainting","volume":"632","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.116222_b55","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"6813","article-title":"TransCNN-HAE: Transformer-CNN hybrid autoencoder for blind image inpainting","author":"Zhao","year":"2022"},{"key":"10.1016\/j.knosys.2026.116222_b56","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"Vol. 139","author":"Radford","year":"2021"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009482?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009482?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:04:19Z","timestamp":1780016659000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126009482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":56,"alternative-id":["S0950705126009482"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116222","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Text image inpainting via Text-Referenced Residual Diffusion Model in latent space","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116222","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116222"}}