{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T16:41:47Z","timestamp":1771260107962,"version":"3.50.1"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726422","type":"print"},{"value":"9783031726439","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-72643-9_5","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T20:47:32Z","timestamp":1732222052000},"page":"70-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["FreeCompose: Generic Zero-Shot Image Composition with\u00a0Diffusion Prior"],"prefix":"10.1007","author":[{"given":"Zhekai","family":"Chen","sequence":"first","affiliation":[]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Zeqing","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graph. (2023)","DOI":"10.1145\/3592450"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: zero-shot object-level image customization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Fang, L., Ye, L., Zhang, Q.: Deep video harmonization by improving spatial-temporal consistency. J. Mach. Learn. Res. (2024)","DOI":"10.1007\/s11633-023-1447-3"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Cohen-Or, D., Sorkine, O., Gal, R., Leyvand, T., Xu, Y.Q.: Color harmonization. ACM Trans. Graph. (2006)","DOI":"10.1145\/1179352.1141933"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Cong, W., Niu, L., Zhang, J., Liang, J., Zhang, L.: Bargainnet: background-guided domain translation for image harmonization. arXiv: Compress. Res. Repository (2020)","DOI":"10.1109\/ICME51207.2021.9428394"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Cong, W., et al.: Dovenet: deep image harmonization via domain verification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: On-demand learning for deep image restoration. In: Proceedings of IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.124"},{"key":"5_CR10","unstructured":"Hao, G., Iizuka, S., Fukui, K.: Image harmonization with attention-based deep feature modulation. Trans. Mach. Learn. Res. (2020)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Hertz, A., Aberman, K., Cohen-Or, D.: Delta denoising score. In: Proceedings of IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"5_CR12","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv: Comp. Res. Repository (2022)"},{"key":"5_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Proceedings of Advances in Neural Information Processing Systems (2020)"},{"key":"5_CR14","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv: Comp. Res. Repository (2022)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Huang, J., Liu, Y., Qin, J., Chen, S.: KV inversion: KV embeddings learning for text-conditioned real image action editing. arXiv: Comp. Res. Repository (2023)","DOI":"10.1007\/978-981-99-8429-9_14"},{"key":"5_CR16","unstructured":"Huang, Y., et al.: Diffusion model-based image editing: a survey. arXiv: Comp. Res. Repository (2024)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Iizuka, S., Simo-Serra, E., Ishikawa, H.: Globally and locally consistent image completion. ACM Trans. Graph. (2017)","DOI":"10.1145\/3072959.3073659"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: SSH: a self-supervised framework for image harmonization. arXiv: Comp. Res. Repository (2021)","DOI":"10.1109\/ICCV48922.2021.00479"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. arXiv: Comp. Res. Repository (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"5_CR21","unstructured":"Katzir, O., Patashnik, O., Cohen-Or, D., Lischinski, D.: Noise-free score distillation. arXiv: Comp. Res. Repository (2023)"},{"key":"5_CR22","unstructured":"Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. arXiv: Comp. Res. Repository (2017)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Pattern Recogn. (2015)","DOI":"10.1038\/nature14539"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Ling, J., Xue, H., Song, L., Xie, R., Gu, X.: Region-aware adaptive instance normalization for image harmonization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00924"},{"key":"5_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01252-6_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Liu","year":"2018","unstructured":"Liu, G., Reda, F.A., Shih, K.J., Wang, T.-C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 89\u2013105. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_6"},{"key":"5_CR27","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 IEEE Conference Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv: Comp. Res. Repository (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Mustafa, A., Mantiuk, R.K.: Transformation consistency regularization - a semi-supervised paradigm for image-to-image translation. arXiv: Comp. Res. Repository (2020)","DOI":"10.1007\/978-3-030-58523-5_35"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleClip: text-driven manipulation of styleGAN imagery. arXiv: Comp. Res. Repository (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: Feature learning by inpainting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Pitie, F., Kokaram, A.C., Dahyot, R.: N-dimensional probability density function transfer and its application to color transfer. In: Tenth IEEE International Conference on Computer Vision (ICCV\u201905), vol. 1 (2005)","DOI":"10.1109\/ICCV.2005.166"},{"key":"5_CR33","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv: Comp. Res. Repository (2023)"},{"key":"5_CR34","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv: Comp. Res. Repository (2022)"},{"key":"5_CR35","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv: Comp. Res. Repository (2022)"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Reinhard, E., Adhikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Computer Graphics and Applications (2001)","DOI":"10.1109\/38.946629"},{"key":"5_CR37","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 IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR38","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 IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"5_CR39","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Proceedings of Advances in Neural Information Processing Systems (2022)"},{"key":"5_CR40","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv: Comp. Res. Repository (2014)"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Sofiiuk, K., Popenova, P., Konushin, A.: Foreground-aware semantic representations for image harmonization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2021)","DOI":"10.1109\/WACV48630.2021.00166"},{"key":"5_CR42","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: Proceedings of Machine Learning Research (2015)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Sunkavalli, K., Johnson, M.K., Matusik, W., Pfister, H.: Multi-scale image harmonization. ACM Trans. Graph. (2010)","DOI":"10.1145\/1833351.1778862"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with Fourier convolutions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Tan, L., Li, J., Niu, L., Zhang, L.: Deep image harmonization in dual color spaces. arXiv: Comp. Res. Repository (2023)","DOI":"10.1145\/3581783.3612404"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Tao, M.W., Johnson, M.K., Paris, S.: Error-tolerant image compositing. Int. J. Comput. Vision (2013)","DOI":"10.1007\/s11263-012-0579-7"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B., Tang, H., Wu, F., Wei, L., Tian, Q.: De-net: dynamic text-guided image editing adversarial networks. In: Proceedings of the AAAI Conference on Artificial Intelligence (2022)","DOI":"10.1609\/aaai.v37i8.26189"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Shen, X., Lin, Z., Sunkavalli, K., Lu, X., Yang, M.H.: Deep image harmonization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.299"},{"key":"5_CR49","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: Proceedings of Advances in Neural Information Processing Systems (2024)"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Xia, W., Yang, Y., Xue, J.H., Wu, B.: TediGAN: text-guided diverse face image generation and manipulation. arXiv: Comp. Res. Repository (2020)","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Yang, C., Lu, X., Lin, Z.L., Shechtman, E., Wang, O., Li, H.: High-resolution image inpainting using multi-scale neural patch synthesis. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2017.434"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Zhan, F., et al.: Multimodal image synthesis and editing: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3305243"},{"key":"5_CR54","unstructured":"Zhang, R., Che, T., Ghahramani, Z., Bengio, Y., Song, Y.: MetaGAN: an adversarial approach to few-shot learning. In: Proceedings of Advances in Neural Information Processing Systems (2018)"},{"key":"5_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Krahenbuhl, P., Shechtman, E., Efros, A.A.: Learning a discriminative model for the perception of realism in composite images. In: Proceedings of IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.449"},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.244"}],"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\/978-3-031-72643-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T21:25:00Z","timestamp":1732224300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72643-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726422","9783031726439"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72643-9_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 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"}}]}}