{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T05:47:06Z","timestamp":1749016026830,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783883"},{"type":"electronic","value":"9783031783890"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-78389-0_22","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T14:16:18Z","timestamp":1733321778000},"page":"326-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["NR-CION: Non-rigid Consistent Image Composition Via Diffusion Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5744-0574","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5627-7522","authenticated-orcid":false,"given":"Liuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0967-4859","authenticated-orcid":false,"given":"Jun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2stylegan: How to embed images into the stylegan latent space? In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 4432\u20134441 (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"issue":"4","key":"22_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Transactions on Graphics (TOG) 42(4), 1\u201311 (2023)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"22_CR4","doi-asserted-by":"publisher","first-page":"2570","DOI":"10.1007\/s11263-020-01336-9","volume":"128","author":"S Azadi","year":"2020","unstructured":"Azadi, S., Pathak, D., Ebrahimi, S., Darrell, T.: Compositional gan: Learning image-conditional binary composition. Int. J. Comput. Vision 128, 2570\u20132585 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: Learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"issue":"4","key":"22_CR6","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1145\/245.247","volume":"2","author":"PJ Burt","year":"1983","unstructured":"Burt, P.J., Adelson, E.H.: A multiresolution spline with application to image mosaics. ACM Transactions on Graphics (TOG) 2(4), 217\u2013236 (1983)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 22560\u201322570 (October 2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"22_CR8","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: Diffedit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Crowson, K., Biderman, S., Kornis, D., Stander, D., Hallahan, E., Castricato, L., Raff, E.: Vqgan-clip: Open domain image generation and editing with natural language guidance. In: European Conference on Computer Vision. pp. 88\u2013105. Springer (2022)","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Dong, W., Xue, S., Duan, X., Han, S.: Prompt tuning inversion for text-driven image editing using diffusion models. arXiv preprint arXiv:2305.04441 (2023)","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"22_CR11","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"22_CR12","unstructured":"Ju, X., Zeng, A., Bian, Y., Liu, S., Xu, Q.: Direct inversion: Boosting diffusion-based editing with 3 lines of code. International Conference on Learning Representations (2023)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., Mosseri, I., Irani, M.: Imagic: Text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Ke, Z., Sun, C., Zhu, L., Xu, K., Lau, R.W.: Harmonizer: Learning to perform white-box image and video harmonization. In: European Conference on Computer Vision. pp. 690\u2013706. Springer (2022)","DOI":"10.1007\/978-3-031-19784-0_40"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, P., Zhang, L., Huang, Q., He, X., Lyu, S., Gao, J.: Object-driven text-to-image synthesis via adversarial training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12174\u201312182 (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: European Conference on Computer Vision. pp. 423\u2013439. Springer (2022)","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Li, C., Yang, J., Su, H., Zhu, J., et\u00a0al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Lu, S., Liu, Y., Kong, A.W.K.: Tf-icon: Diffusion-based training-free cross-domain image composition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2294\u20132305 (2023)","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"22_CR20","unstructured":"Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.Y., Ermon, S.: SDEdit: Guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2022)"},{"key":"22_CR21","unstructured":"Miyake, D., Iohara, A., Saito, Y., Tanaka, T.: Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models. arXiv preprint arXiv:2305.16807 (2023)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Porter, T., Duff, T.: Compositing digital images. In: Proceedings of the 11th annual conference on Computer graphics and interactive techniques. pp. 253\u2013259 (1984)","DOI":"10.1145\/800031.808606"},{"key":"22_CR24","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"22_CR25","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":"22_CR26","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":"22_CR27","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR28","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. International Conference on Learning Representations (2021)"},{"key":"22_CR29","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/s11263-012-0579-7","volume":"103","author":"MW Tao","year":"2013","unstructured":"Tao, M.W., Johnson, M.K., Paris, S.: Error-tolerant image compositing. Int. J. Comput. Vision 103, 178\u2013189 (2013)","journal-title":"Int. J. Comput. Vision"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Yu, Y., Zhou, K., Xu, D., Shi, X., Bao, H., Guo, B., Shum, H.Y.: Mesh editing with poisson-based gradient field manipulation. In: ACM SIGGRAPH 2004 Papers, pp. 644\u2013651 (2004)","DOI":"10.1145\/1186562.1015774"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, J., Perazzi, F., Lin, Z., Patel, V.M.: Deep image compositing. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision. pp. 365\u2013374 (2021)","DOI":"10.1109\/WACV48630.2021.00041"},{"key":"22_CR32","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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78389-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T15:08:38Z","timestamp":1733324918000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78389-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031783883","9783031783890"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78389-0_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}