{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T13:20:42Z","timestamp":1786108842762,"version":"3.56.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732461","type":"print"},{"value":"9783031732478","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73247-8_6","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:02:20Z","timestamp":1730376140000},"page":"92-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["AnyControl: Create Your Artwork with\u00a0Versatile Control on\u00a0Text-to-Image Generation"],"prefix":"10.1007","author":[{"given":"Yanan","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanchen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinhao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: Spatext: Spatio-textual representation for controllable image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"6_CR2","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: Multidiffusion: Fusing diffusion paths for controlled image generation (2023)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bashkirova, D., Lezama, J., Sohn, K., Saenko, K., Essa, I.: Masksketch: unpaired structure-guided masked image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00187"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Canny, J.: A computational approach to edge detection. TPAMI PAMI-8(6), 679\u2013698 (1986)","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"6_CR6","unstructured":"Cheng, J., Liang, X., Shi, X., He, T., Xiao, T., Li, M.: Layoutdiffuse: adapting foundational diffusion models for layout-to-image generation. arXiv preprint arXiv:2302.08908 (2023)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Couairon, G., Careil, M., Cord, M., Lathuili\u00e8re, S., Verbeek, J.: Zero-shot spatial layout conditioning for text-to-image diffusion models. In: ICCV, pp. 2174\u20132183 (2023)","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"6_CR8","series-title":"LNCS","first-page":"89","volume-title":"ECCV 2022","author":"O Gafni","year":"2022","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13675, pp. 89\u2013106. Springer, Cham (2022)"},{"key":"6_CR9","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"6_CR12","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. NeurIPS 30 (2017)"},{"key":"6_CR13","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":"6_CR14","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"6_CR15","unstructured":"Hu, M., et al.: Cocktail: mixing multi-modality control for text-conditional image generation. In: NeurIPS (2023)"},{"key":"6_CR16","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Jia, C., et al.: SSMG: spatial-semantic map guided diffusion model for free-form layout-to-image generation. arXiv preprint arXiv:2308.10156 (2023)","DOI":"10.1609\/aaai.v38i3.28024"},{"key":"6_CR18","unstructured":"Kim, S., Lee, J., Hong, K., Kim, D., Ahn, N.: Diffblender: scalable and composable multimodal text-to-image diffusion models. arXiv preprint arXiv:2305.15194 (2023)"},{"issue":"7","key":"6_CR19","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. IJCV 128(7), 1956\u20131981 (2020)","journal-title":"IJCV"},{"key":"6_CR20","unstructured":"Lee, J., Cho, H., Yoo, Y., Kim, S.B., Jeong, Y.: Compose and conquer: diffusion-based 3D depth aware composable image synthesis. In: ICLR (2024)"},{"key":"6_CR21","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":"6_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Gligen: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"6_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Mo, S., et al.: Freecontrol: training-free spatial control of any text-to-image diffusion model with any condition. arXiv preprint arXiv:2312.07536 (2023)","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"6_CR25","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 preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"6_CR26","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Qi, L., et al.: High quality entity segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00374"},{"key":"6_CR28","unstructured":"Qin, C., et\u00a0al.: Unicontrol: a unified diffusion model for controllable visual generation in the wild. arXiv preprint arXiv:2305.11147 (2023)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Qu, L., Wu, S., Fei, H., Nie, L., Chua, T.S.: Layoutllm-t2i: eliciting layout guidance from LLM for text-to-image generation. In: MM (2023)","DOI":"10.1145\/3581783.3612012"},{"key":"6_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"6_CR31","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":"6_CR32","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. TPAMI 44(3) (2022)","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"6_CR33","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":"6_CR34","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":"6_CR35","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":"6_CR36","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. NeurIPS 35, 36479\u201336494 (2022)","journal-title":"NeurIPS"},{"key":"6_CR37","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. NeurIPS 35, 25278\u201325294 (2022)","journal-title":"NeurIPS"},{"key":"6_CR38","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X., Darrell, T., Rambhatla, S.S., Girdhar, R., Misra, I.: Instancediffusion: instance-level control for image generation (2024)","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., Shou, M.Z.: Boxdiff: text-to-image synthesis with training-free box-constrained diffusion. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, Y., Chen, Z., Wang, G., Liang, X., Lin, L.: Law-diffusion: complex scene generation by diffusion with layouts. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02072"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., et\u00a0al.: Reco: region-controlled text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"6_CR43","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"6_CR45","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. NeurIPS 36 (2024)"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, G., Zhou, X., Li, X., Qi, Z., Shan, Y., Li, X.: Layoutdiffusion: controllable diffusion model for layout-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Zeng, Y., Liu, W., Yuan, C., Chen, K.: A task is worth one word: learning with task prompts for high-quality versatile image inpainting. arXiv preprint arXiv:2312.03594 (2023)","DOI":"10.1007\/978-3-031-73636-0_12"}],"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\/978-3-031-73247-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T15:37:20Z","timestamp":1732981040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73247-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732461","9783031732478"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73247-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}