{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T08:58:43Z","timestamp":1777712323237,"version":"3.51.4"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734106","type":"print"},{"value":"9783031734113","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-73411-3_23","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T20:08:14Z","timestamp":1732306094000},"page":"402-418","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["SwapAnything: Enabling Arbitrary Object Swapping in\u00a0Personalized Image Editing"],"prefix":"10.1007","author":[{"given":"Jing","family":"Gu","sequence":"first","affiliation":[]},{"given":"Nanxuan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhifei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"He","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"HyunJoon","family":"Jung","sequence":"additional","affiliation":[]},{"given":"Yilin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xin Eric","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"issue":"4","key":"23_CR1","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 Trans. Graph. (TOG) 42(4), 1\u201311 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"23_CR2","unstructured":"Blattmann, A., Rombach, R., Oktay, K., M\u00fcller, J., Ommer, B.: Retrieval-augmented diffusion models. In: NIPS (2022)"},{"key":"23_CR3","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: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"23_CR4","unstructured":"Chen, H., Zhang, Y., Wang, X., Duan, X., Zhou, Y., Zhu, W.: Disenbooth: identity-preserving disentangled tuning for subject-driven text-to-image generation (2023)"},{"key":"23_CR5","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. arXiv (2023)"},{"key":"23_CR6","unstructured":"Choi, J., Choi, Y., Kim, Y., Kim, J., Yoon, S.: Custom-edit: text-guided image editing with customized diffusion models. arXiv preprint arXiv:2305.15779 (2023)"},{"key":"23_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/978-3-031-19836-6_6","volume-title":"Computer Vision - ECCV 2022","author":"K Crowson","year":"2022","unstructured":"Crowson, K., et al.: VQGAN-clip: open domain image generation and editing with natural language guidance. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 88\u2013105. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_6"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Deng, Y., et al.: Stytr2: image style transfer with transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"23_CR9","unstructured":"Ding, M., et\u00a0al.: CogView: mastering text-to-image generation via transformers. In: NIPS (2021)"},{"key":"23_CR10","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. In: Advances in Neural Information Processing Systems (2023)"},{"key":"23_CR11","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. In: ICLR (2023)"},{"key":"23_CR12","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"23_CR13","unstructured":"Gu, J., et al.: PhotoSwap: personalized subject swapping in images (2023)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Gu, Y., et al.: VideoSwap: customized video subject swapping with interactive semantic point correspondence. arXiv preprint arXiv:2312.02087 (2023)","DOI":"10.1109\/CVPR52733.2024.00728"},{"key":"23_CR15","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"23_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179\u2013196. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_11"},{"key":"23_CR17","unstructured":"Jahn, M., Rombach, R., Ommer, B.: High-resolution complex scene synthesis with transformers. arXiv (2021)"},{"key":"23_CR18","unstructured":"Jia, X., et al.: Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. arXiv preprint arXiv:2304.02642 (2023)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"23_CR20","unstructured":"Li, D., Li, J., Hoi, S.C.: Blip-diffusion: pre-trained subject representation for controllable text-to-image generation and editing. In: Advances in Neural Information Processing Systems (2023)"},{"key":"23_CR21","unstructured":"Li, T., Ku, M., Wei, C., Chen, W.: DreamEdit: subject-driven image editing. arXiv preprint arXiv:2306.12624 (2023)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GliGen: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Liao, J., Yao, Y., Yuan, L., Hua, G., Kang, S.B.: Visual attribute transfer through deep image analogy. ACM Trans. Graph. (2017)","DOI":"10.1145\/3072959.3073683"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: AdaAttn: revisit attention mechanism in arbitrary neural style transfer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"23_CR25","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2022)"},{"key":"23_CR26","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":"23_CR27","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":"23_CR28","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Garibi, D., Azuri, I., Averbuch-Elor, H., Cohen-Or, D.: Localizing object-level shape variations with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"23_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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_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. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"23_CR32","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Seo, J., Lee, G., Cho, S., Lee, J., Kim, S.: MidMS: matching interleaved diffusion models for exemplar-based image translation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2191\u20132199 (2023)","DOI":"10.1609\/aaai.v37i2.25313"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: Instantbooth: personalized text-to-image generation without test-time finetuning (2023)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"23_CR35","unstructured":"Simsar, E., Tonioni, A., Xian, Y., Hofmann, T., Tombari, F.: Lime: localized image editing via attention regularization in diffusion models. arXiv preprint arXiv:2312.09256 (2023)"},{"key":"23_CR36","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Tewel, Y., Gal, R., Chechik, G., Atzmon, Y.: Key-locked rank one editing for text-to-image personalization. In: ACM SIGGRAPH 2023 Conference Proceedings. SIGGRAPH \u201923 (2023)","DOI":"10.1145\/3588432.3591506"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Wang, M., et al.: Example-guided style-consistent image synthesis from semantic labeling. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00159"},{"key":"23_CR40","unstructured":"Wang, Q., Bai, X., Wang, H., Qin, Z., Chen, A.: InstantID: zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:2401.07519 (2024)"},{"key":"23_CR41","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":"23_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., et\u00a0al.: Reco: region-controlled text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14246\u201314255 (2023)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: Scenecomposer: any-level semantic image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22468\u201322478 (2023)","DOI":"10.1109\/CVPR52729.2023.02152"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"23_CR45","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: CVPR, pp. 5143\u20135153 (2020)","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"23_CR46","unstructured":"Zhang, Y., et al.: Inversion-based creativity transfer with diffusion models. arXiv (2022)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Cocosnet v2: full-resolution correspondence learning for image translation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01130"}],"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\/978-3-031-73411-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T21:28:09Z","timestamp":1732310889000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73411-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031734106","9783031734113"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73411-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 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"}}]}}