{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:56:38Z","timestamp":1781585798289,"version":"3.54.5"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727504","type":"print"},{"value":"9783031727511","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72751-1_15","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:52:13Z","timestamp":1729849933000},"page":"253-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["OMG: Occlusion-Friendly Personalized Multi-concept Generation in\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"given":"Zhe","family":"Kong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaihao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bizhu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanying","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"issue":"6","key":"15_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618322","volume":"42","author":"Y Alaluf","year":"2023","unstructured":"Alaluf, Y., Richardson, E., Metzer, G., Cohen-Or, D.: A neural space-time representation for text-to-image personalization. ACM TOG 42(6), 1\u201310 (2023)","journal-title":"ACM TOG"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Arar, M., et al.: Domain-agnostic tuning-encoder for fast personalization of text-to-image models. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618173"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Aberman, K., Fried, O., Cohen-Or, D., Lischinski, D.: Break-a-scene: Extracting multiple concepts from a single image. arXiv preprint arXiv:2305.16311 (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"15_CR4","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: Fusing diffusion paths for controlled image generation. arXiv preprint arXiv:2302.08113 (2023)"},{"key":"15_CR5","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3) (2023). https:\/\/cdnopenai.com\/papers\/dall-e-3.pdf"},{"key":"15_CR6","unstructured":"Chae, D., Park, N., Kim, J., Lee, K.: InstructBooth: Instruction-following personalized text-to-image generation. arXiv preprint arXiv:2312.03011 (2023)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"15_CR8","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)"},{"key":"15_CR9","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":"15_CR10","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":"15_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: CVPR, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"15_CR12","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2022)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228 (2023)","DOI":"10.1145\/3592133"},{"issue":"4","key":"15_CR14","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 TOG 42(4), 1\u201313 (2023)","journal-title":"ACM TOG"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Gong, Y., et al.: TaleCrafter: interactive story visualization with multiple characters. In: SIGGRAPH Asia (2023)","DOI":"10.1145\/3610548.3618184"},{"key":"15_CR16","unstructured":"Gu, Y., et\u00a0al.: Mix-of-show: decentralized low-rank adaptation for multi-concept customization of diffusion models. In: NIPS (2023)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D., Yang, F.: SVDiff: Compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305 (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"15_CR18","unstructured":"Hao, S., Han, K., Zhao, S., Wong, K.Y.K.: ViCo: Detail-preserving visual condition for personalized text-to-image generation. arXiv preprint arXiv:2306.00971 (2023)"},{"key":"15_CR19","unstructured":"He, X., Cao, Z., Kolkin, N., Yu, L., Rhodin, H., Kalarot, R.: A data perspective on enhanced identity preservation for diffusion personalization. arXiv preprint arXiv:2311.04315 (2023)"},{"key":"15_CR20","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":"15_CR21","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS 33, 6840\u20136851 (2020)","journal-title":"NeurIPS"},{"key":"15_CR22","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2021)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"15_CR24","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"15_CR25","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: CVPR, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"15_CR26","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M.M., Shan, Y.: PhotoMaker: Customizing realistic human photos via stacked ID embedding. arXiv preprint arXiv:2312.04461 (2023)","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"15_CR28","unstructured":"Liu, Z., et al.: Cones 2: Customizable image synthesis with multiple subjects. arXiv preprint arXiv:2305.19327 (2023)"},{"key":"15_CR29","unstructured":"Ma, Y., Yang, H., Wang, W., Fu, J., Liu, J.: Unified multi-modal latent diffusion for joint subject and text conditional image generation. arXiv preprint arXiv:2303.09319 (2023)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Pang, L., Yin, J., Xie, H., Wang, Q., Li, Q., Mao, X.: Cross initialization for personalized text-to-image generation. arXiv preprint arXiv:2312.15905 (2023)","DOI":"10.1109\/CVPR52733.2024.00802"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Po, R., Yang, G., Aberman, K., Wetzstein, G.: Orthogonal adaptation for modular customization of diffusion models. arXiv preprint arXiv:2312.02432 (2023)","DOI":"10.1109\/CVPR52733.2024.00761"},{"key":"15_CR32","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR33","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, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: HyperDreamBooth: Hypernetworks for fast personalization of text-to-image models. arXiv preprint arXiv:2307.06949 (2023)","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"15_CR35","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. NIPS 35, 36479\u201336494 (2022)","journal-title":"NIPS"},{"key":"15_CR36","unstructured":"Schuhmann, C., et al.: LAION-400M: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: InstantBooth: Personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411 (2023)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"15_CR38","unstructured":"Smith, J.S., et al.: Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA. arXiv preprint arXiv:2304.06027 (2023)"},{"key":"15_CR39","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2020)"},{"key":"15_CR40","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, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591506"},{"key":"15_CR41","unstructured":"Tunanyan, H., Xu, D., Navasardyan, S., Wang, Z., Shi, H.: Multi-concept T2I-Zero: Tweaking only the text embeddings and nothing else. arXiv preprint arXiv:2310.07419 (2023)"},{"issue":"6","key":"15_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618315","volume":"42","author":"Y Vinker","year":"2023","unstructured":"Vinker, Y., Voynov, A., Cohen-Or, D., Shamir, A.: Concept decomposition for visual exploration and inspiration. ACM TOG 42(6), 1\u201313 (2023)","journal-title":"ACM TOG"},{"key":"15_CR43","unstructured":"Voynov, A., Chu, Q., Cohen-Or, D., Aberman, K.: $$ p+ $$: Extended textual conditioning in text-to-image generation. arXiv preprint arXiv:2303.09522 (2023)"},{"key":"15_CR44","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":"15_CR45","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. arXiv preprint arXiv:2302.13848 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Xiao, G., Yin, T., Freeman, W.T., Durand, F., Han, S.: FastComposer: Tuning-free multi-subject image generation with localized attention. arXiv preprint arXiv:2305.10431 (2023)","DOI":"10.1007\/s11263-024-02227-z"},{"key":"15_CR47","unstructured":"Yan, Y., et al.: FaceStudio: Put your face everywhere in seconds. arXiv preprint arXiv:2312.02663 (2023)"},{"key":"15_CR48","unstructured":"Zhang, X.L., et al.: Compositional inversion for stable diffusion models. arXiv preprint arXiv:2312.08048 (2023)"},{"key":"15_CR49","unstructured":"Zhao, R., Zhu, M., Dong, S., Wang, N., Gao, X.: CatVersion: Concatenating embeddings for diffusion-based text-to-image personalization. arXiv preprint arXiv:2311.14631 (2023)"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, R., Gu, J., Sun, T.: Customization assistant for text-to-image generation. arXiv preprint arXiv:2312.03045 (2023)","DOI":"10.1109\/CVPR52733.2024.00877"},{"key":"15_CR51","unstructured":"Zhou, Y., Zhang, R., Sun, T., Xu, J.: Enhancing detail preservation for customized text-to-image generation: A regularization-free approach. arXiv preprint arXiv:2305.13579 (2023)"}],"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\/978-3-031-72751-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:49:38Z","timestamp":1732952978000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72751-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031727504","9783031727511"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72751-1_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 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"}}]}}