{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:56:49Z","timestamp":1784905009875,"version":"3.55.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726262","type":"print"},{"value":"9783031726279","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-3-031-72627-9_3","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"39-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Editable Image Elements for\u00a0Controllable Synthesis"],"prefix":"10.1007","author":[{"given":"Jiteng","family":"Mu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Micha\u00ebl","family":"Gharbi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eli","family":"Shechtman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuno","family":"Vasconcelos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taesung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"3_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 International Conference on Computer Vision (ICCV), pp. 4432\u20134441 (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"issue":"11","key":"3_CR2","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., S\u00fcsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274\u20132282 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: Spatext: spatio-textual representation for controllable image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18370\u201318380 (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: Learning to follow image editing instructions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"3_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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"3_CR6","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"3_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 International Conference on Computer Vision (ICCV), pp. 22560\u201322570 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: zero-shot object-level image customization. arXiv preprint arXiv:2307.09481 (2023)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"3_CR9","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. In: Conference on Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Epstein, D., Park, T., Zhang, R., Shechtman, E., Efros, A.A.: Blobgan: spatially disentangled scene representations. In: European Conference on Computer Vision (ECCV), pp. 616\u2013635 (2022)","DOI":"10.1007\/978-3-031-19784-0_36"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"3_CR12","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. In: International Conference on Learning Representations (ICLR) (2022)"},{"issue":"4","key":"3_CR13","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. 42(4), 1\u201313 (2023)","journal-title":"ACM Trans. Graph."},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Ge, S., Park, T., Zhu, J.Y., Huang, J.B.: Expressive text-to-image generation with rich text. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7545\u20137556 (2023)","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3_CR16","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":"3_CR17","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 the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"3_CR18","unstructured":"Jahn, M., Rombach, R., Ommer, B.: High-resolution complex scene synthesis with transformers. arXiv preprint arXiv:2105.06458 (2021)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"3_CR21","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"3_CR22","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 the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"3_CR23","unstructured":"Li, F., et al.: Semantic-SAM: segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767 (2023)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Gligen: open-set grounded text-to-image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Li, Z., Wu, J., Koh, I., Tang, Y., Sun, L.: Image synthesis from layout with locality-aware mask adaption. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 13819\u201313828 (2021)","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"3_CR26","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 (ECCV), pp. 423\u2013439 (2022)","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"3_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 the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Luo, G., Darrell, T., Wang, O., Goldman, D.B., Holynski, A.: Readout guidance: learning control from diffusion features. arXiv preprint arXiv:2312.02150 (2023)","DOI":"10.1109\/CVPR52733.2024.00785"},{"key":"3_CR29","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 (ICLR) (2021)"},{"key":"3_CR30","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Mu, J., et al.: Coordgan: self-supervised dense correspondences emerge from GANs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00977"},{"key":"3_CR32","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"3_CR33","unstructured":"Park, T., et al.: Swapping autoencoder for deep image manipulation. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Parmar, G., Kumar\u00a0Singh, K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"3_CR36","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)"},{"key":"3_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 the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10674\u201310685 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3_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 the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"3_CR39","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"3_CR40","unstructured":"Schuhmann, C., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Shi, Y., Xue, C., Pan, J., Zhang, W., Tan, V.Y., Bai, S.: Dragdiffusion: harnessing diffusion models for interactive point-based image editing. arXiv preprint arXiv:2306.14435 (2023)","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"3_CR42","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Sun, W., Wu, T.: Learning layout and style reconfigurable GANs for controllable image synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5070\u20135087 (2021)","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Sylvain, T., Zhang, P., Bengio, Y., Hjelm, R.D., Sharma, S.: Object-centric image generation from layouts. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a035, pp. 2647\u20132655 (2021)","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for stylegan image manipulation. ACM Trans. Graph. 40(4), 1\u201314 (2021)","DOI":"10.1145\/3476576.3476706"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Voynov, A., Abernan, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. arXiv preprint arXiv:2211.13752 (2022)","DOI":"10.1145\/3588432.3591560"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Wallace, B., Gokul, A., Naik, N.: Edict: exact diffusion inversion via coupled transformations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22532\u201322541 (2023)","DOI":"10.1109\/CVPR52729.2023.02158"},{"key":"3_CR48","unstructured":"Wang, Q., Wang, Y., Birsak, M., Wonka, P.: Blobgan-3d: a spatially-disentangled 3d-aware generative model for indoor scenes. arXiv preprint arXiv:2303.14706 (2023)"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18381\u201318391 (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"3_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, D., Wang, C., Yang, J., Tao, D.: Modeling image composition for complex scene generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7764\u20137773 (2022)","DOI":"10.1109\/CVPR52688.2022.00761"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, B., Meng, L., Yin, W., Sigal, L.: Image generation from layout. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8584\u20138593 (2019)","DOI":"10.1109\/CVPR.2019.00878"}],"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\/978-3-031-72627-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T22:45:06Z","timestamp":1732920306000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 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"}}]}}