{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:40:53Z","timestamp":1769186453660,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556816","type":"print"},{"value":"9789819556823","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\/978-981-95-5682-3_33","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:05Z","timestamp":1769116385000},"page":"470-484","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Online Data Augmentation and\u00a0Subject Enhancement for\u00a0Context-Aware Image Inpainting"],"prefix":"10.1007","author":[{"given":"Huanghao","family":"Yin","sequence":"first","affiliation":[]},{"given":"Jing","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Junhai","family":"Yong","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Alaluf, Y., Tov, O., Mokady, R., Gal, R., Bermano, A.: Hyperstyle: StyleGAN inversion with hypernetworks for real image editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18511\u201318521 (2022)","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"33_CR2","unstructured":"Bau, D., et al.: Semantic photo manipulation with a generative image prior. arXiv preprint arXiv:2005.07727 (2020)"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Zero-shot image editing with reference imitation. arXiv preprint arXiv:2406.07547 (2024)","DOI":"10.52202\/079017-2669"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Corneanu, C., Gadde, R., Martinez, A.M.: LatentPaint: image inpainting in latent space with diffusion models. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4334\u20134343 (2024)","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"33_CR5","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)"},{"issue":"4","key":"33_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592133","volume":"42","author":"R Gal","year":"2023","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Encoder-based domain tuning for fast personalization of text-to-image models. ACM Trans. Graph. (TOG) 42(4), 1\u201313 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Gu, S., Bao, J., Yang, H., Chen, D., Wen, F., Yuan, L.: Mask-guided portrait editing with conditional GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3436\u20133445 (2019)","DOI":"10.1109\/CVPR.2019.00355"},{"key":"33_CR8","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":"33_CR9","unstructured":"HuggingFace, Contributors: stable-diffusion-inpainting (2024). https:\/\/huggingface.co\/stable-diffusion-v1-5\/stable-diffusion-inpainting"},{"key":"33_CR10","unstructured":"Hui, Z., Li, J., Wang, X., Gao, X.: Image fine-grained inpainting. arXiv preprint arXiv:2002.02609 (2020)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Lin, Y., Chen, Y.W., Tsai, Y.H., Jiang, L., Yang, M.H.: Text-driven image editing via learnable regions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7059\u20137068 (2024)","DOI":"10.1109\/CVPR52733.2024.00674"},{"key":"33_CR12","first-page":"16331","volume":"34","author":"H Ling","year":"2021","unstructured":"Ling, H., Kreis, K., Li, D., Kim, S.W., Torralba, A., Fidler, S.: EditGAN: high-precision semantic image editing. Adv. Neural. Inf. Process. Syst. 34, 16331\u201316345 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/978-3-030-58536-5_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Liu","year":"2020","unstructured":"Liu, H., Jiang, B., Song, Y., Huang, W., Yang, C.: Rethinking image inpainting via a mutual encoder-decoder with feature equalizations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part II. LNCS, vol. 12347, pp. 725\u2013741. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_43"},{"key":"33_CR14","unstructured":"Lu, L., Li, J., Zhang, B., Niu, L.: DreamCom: finetuning text-guided inpainting model for image composition. arXiv preprint arXiv:2309.15508 (2023)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"33_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1007\/978-3-030-67070-2_43","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"E Ntavelis","year":"2020","unstructured":"Ntavelis, E., et al.: AIM 2020 challenge on image extreme inpainting. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020, Part III. LNCS, vol. 12537, pp. 716\u2013741. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-67070-2_43"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Peng, J., Liu, D., Xu, S., Li, H.: Generating diverse structure for image inpainting with hierarchical VQ-VAE. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10775\u201310784 (2021)","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"33_CR20","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022). 1(2), 3"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Ren, Y., Yu, X., Zhang, R., Li, T.H., Liu, S., Li, G.: StructureFlow: image inpainting via structure-aware appearance flow. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 181\u2013190 (2019)","DOI":"10.1109\/ICCV.2019.00027"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: 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":"33_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":"33_CR24","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of GANs for semantic face editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9243\u20139252 (2020)","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"33_CR26","unstructured":"ThereforeGames: txt2mask (2022). https:\/\/github.com\/ThereforeGames\/txt2mask. Accessed 31 Dec 2024"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, J., Chen, D., Liao, J.: High-fidelity pluralistic image completion with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4692\u20134701 (2021)","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"33_CR28","unstructured":"Wang, T., et al.: Pretraining is all you need for image-to-image translation. arXiv preprint arXiv:2205.12952 (2022)"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: encoding visual concepts into textual embeddings for customized text-to-image generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15943\u201315953 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: SmartBrush: text and shape guided object inpainting with diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22428\u201322437 (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"33_CR31","unstructured":"Xie, S., et al.: DreaminPainter: text-guided subject-driven image inpainting with diffusion models. arXiv preprint arXiv:2312.03771 (2023)"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Personalized face inpainting with diffusion models by parallel visual attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5432\u20135442 (2024)","DOI":"10.1109\/WACV57701.2024.00535"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18381\u201318391 (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Yang, S., Chen, X., Liao, J.: Uni-paint: a unified framework for multimodal image inpainting with pretrained diffusion model. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 3190\u20133199 (2023)","DOI":"10.1145\/3581783.3612200"},{"key":"33_CR35","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Yu, Y., et al.: Diverse image inpainting with bidirectional and autoregressive transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 69\u201378 (2021)","DOI":"10.1145\/3474085.3475436"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Fu, J., Chao, H., Guo, B.: Learning pyramid-context encoder network for high-quality image inpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1486\u20131494 (2019)","DOI":"10.1109\/CVPR.2019.00158"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Chen, D., Yuan, L., Wen, F.: Cross-domain correspondence learning for exemplar-based image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5143\u20135153 (2020)","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, L., et al.: UCTGAN: diverse image inpainting based on unsupervised cross-space translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5741\u20135750 (2020)","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, C., Cham, T.J., Cai, J.: Pluralistic image completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1438\u20131447 (2019)","DOI":"10.1109\/CVPR.2019.00153"},{"key":"33_CR41","unstructured":"Zhengwentai, S.: clip-score: CLIP Score for PyTorch (2023). https:\/\/github.com\/taited\/clip-score. Version 0.1.1"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: CoCosNet V2: full-resolution correspondence learning for image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11465\u201311475 (2021)","DOI":"10.1109\/CVPR46437.2021.01130"},{"key":"33_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, S., Fang, P., Zhu, C., Zhao, Z., Xu, Q., Xue, H.: Text image inpainting via global structure-guided diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 7775\u20137783 (2024)","DOI":"10.1609\/aaai.v38i7.28612"}],"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\/978-981-95-5682-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:15Z","timestamp":1769116395000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5682-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556816","9789819556823"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5682-3_33","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"}}]}}