{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:17:55Z","timestamp":1782317875490,"version":"3.54.5"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733369","type":"print"},{"value":"9783031733376","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73337-6_16","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:02:27Z","timestamp":1730329347000},"page":"275-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["ReGround: Improving Textual and\u00a0Spatial Grounding at\u00a0No Cost"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7614-261X","authenticated-orcid":false,"given":"Phillip Y.","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7428-9570","authenticated-orcid":false,"given":"Minhyuk","family":"Sung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"16_CR1","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"16_CR2","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":"16_CR3","unstructured":"Balaji, Y., et\u00a0al.: eDiffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"16_CR4","unstructured":"Bansal, A., et al.: Universal guidance for diffusion models. In: ICLR (2024)"},{"key":"16_CR5","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. In: ICML (2023)"},{"key":"16_CR6","unstructured":"Betker, J., et al.: Improving image generation with better captions (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"16_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: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"16_CR9","unstructured":"Chen, W.G., Spiridonova, I., Yang, J., Gao, J., Li, C.: LLaVA-interactive: an all-in-one demo for image chat, segmentation, generation and editing. arXiv preprint arXiv:2311.00571 (2023)"},{"key":"16_CR10","unstructured":"Cheng, J., Liang, X., Shi, X., He, T., Xiao, T., Li, M.: LayoutDiffuse: adapting foundational diffusion models for layout-to-image generation. arXiv (2023)"},{"key":"16_CR11","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 (2023)","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"16_CR12","unstructured":"Feng, W., et al.: LayoutGPT: compositional visual planning and generation with large language models. In: NeurIPS (2023)"},{"key":"16_CR13","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. In: ICLR (2022)"},{"key":"16_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-58574-7_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Herzig","year":"2020","unstructured":"Herzig, R., Bar, A., Xu, H., Chechik, G., Darrell, T., Globerson, A.: Learning canonical representations for scene graph to image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 210\u2013227. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_13"},{"key":"16_CR15","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. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"16_CR16","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. In: NeurIPS (2018)"},{"key":"16_CR17","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Hong, S., Yang, D., Choi, J., Lee, H.: Inferring semantic layout for hierarchical text-to-image synthesis. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Hong, S., Lee, G., Jang, W., Kim, S.: Improving sample quality of diffusion models using self-attention guidance. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: Openclip (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"16_CR22","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS (2021)"},{"key":"16_CR23","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":"16_CR24","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.H., Ha, J.W., Zhu, J.Y.: Dense text-to-image generation with attention modulation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"16_CR26","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation. In: NeurIPS (2024)"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Object-driven text-to-image synthesis via adversarial training. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01245"},{"key":"16_CR28","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":"16_CR29","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: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"16_CR30","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":"16_CR31","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Ma, W.D.K., Lewis, J.P., Lahiri, A., Leung, T., Kleijn, W.B.: Directed diffusion: direct control of object placement through attention guidance. arXiv preprint arXiv:2302.13153 (2023)","DOI":"10.1609\/aaai.v38i5.28204"},{"key":"16_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"16_CR34","unstructured":"OpenAI: ChatGPT. https:\/\/chat.openai.com\/"},{"key":"16_CR35","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 TOG (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Phung, Q., Ge, S., Huang, J.B.: Grounded text-to-image synthesis with attention refocusing. arXiv preprint arXiv:2306.05427 (2023)","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"16_CR37","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"16_CR38","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"16_CR39","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":"16_CR40","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"16_CR41","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":"16_CR42","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":"16_CR43","doi-asserted-by":"crossref","unstructured":"Si, C., Huang, Z., Jiang, Y., Liu, Z.: FreeU: Free lunch in diffusion U-Net. arXiv preprint arXiv:2309.11497 (2023)","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"16_CR44","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2021)"},{"key":"16_CR45","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Sun, W., Wu, T.: Image synthesis from reconfigurable layout and style. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01063"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Sylvain, T., Zhang, P., Bengio, Y., Hjelm, R.D., Sharma, S.: Object-centric image generation from layouts. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"16_CR48","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)"},{"key":"16_CR49","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"16_CR50","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. ACM TOG (2023)","DOI":"10.1145\/3588432.3591560"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"16_CR53","unstructured":"Xiao, J., Li, L., Lv, H., Wang, S., Huang, Q.: R &B: region and boundary aware zero-shot grounded text-to-image generation. In: ICLR (2024)"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: BoxDiff: text-to-image synthesis with training-free box-constrained diffusion. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"16_CR55","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":"16_CR56","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, D., Wang, C., Yang, J., Tao, D.: Modeling image composition for complex scene generation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00761"},{"key":"16_CR57","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":"16_CR58","doi-asserted-by":"crossref","unstructured":"Zhao, B., Meng, L., Yin, W., Sigal, L.: Image generation from layout. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00878"},{"key":"16_CR59","unstructured":"Zhao, P., Li, H., Jin, R., Zhou, S.K.: LoCo: locally constrained training-free layout-to-image synthesis. arXiv preprint arXiv:2311.12342 (2023)"},{"key":"16_CR60","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"}],"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\/978-3-031-73337-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:59:59Z","timestamp":1732978799000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73337-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733369","9783031733376"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73337-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 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"}}]}}