{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:41:59Z","timestamp":1777657319991,"version":"3.51.4"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729829","type":"print"},{"value":"9783031729836","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72983-6_19","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"326-343","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Dolfin: Diffusion Layout Transformers Without Autoencoder"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6209-8346","authenticated-orcid":false,"given":"Yilin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2237-1633","authenticated-orcid":false,"given":"Zeyuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3206-778X","authenticated-orcid":false,"given":"Liangjun","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuowen","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Arroyo, D.M., Postels, J., Tombari, F.: Variational transformer networks for layout generation (2021)","DOI":"10.1109\/CVPR46437.2021.01343"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Chai, S., Zhuang, L., Yan, F.: Layoutdm: transformer-based diffusion model for layout generation (2023)","DOI":"10.1109\/CVPR52729.2023.01760"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: Maskgit: masked generative image transformer (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Single-stage diffusion nerf: a unified approach to 3d generation and reconstruction. arXiv preprint arXiv:2304.06714 (2023)","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"19_CR5","unstructured":"Cheng, C.Y., Huang, F., Li, G., Li, Y.: Play: Parametrically conditioned layout generation using latent diffusion (2023)"},{"key":"19_CR6","doi-asserted-by":"publisher","unstructured":"Deka, B., Huang, Z., Franzen, C., Hibschman, J., Afergan, D., Li, Y., Nichols, J., Kumar, R.: Rico: A mobile app dataset for building data-driven design applications. In: UIST 2017 - Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology, pp. 845\u2013854. UIST 2017 - Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology, Association for Computing Machinery, Inc (Oct 2017https:\/\/doi.org\/10.1145\/3126594.3126651, publisher Copyright: 2017 Copyright held by the owner\/author(s).; 30th Annual ACM Symposium on User Interface Software and Technology, UIST 2017 ; Conference date: 22-10-2017 Through 25-10-2017","DOI":"10.1145\/3126594.3126651"},{"key":"19_CR7","doi-asserted-by":"publisher","unstructured":"Deka, B., et al.: Rico: a mobile app dataset for building data-driven design applications. In: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology, UIST 2017, pp. 845\u2013854. Association for Computing Machinery, New York (2017). https:\/\/doi.org\/10.1145\/3126594.3126651. https:\/\/doi.org\/10.1145\/3126594.3126651","DOI":"10.1145\/3126594.3126651"},{"key":"19_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR9","unstructured":"Feng, W., et al.: Layoutgpt: compositional visual planning and generation with large language models. arXiv preprint arXiv:2305.15393 (2023)"},{"key":"19_CR10","unstructured":"Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)"},{"key":"19_CR11","doi-asserted-by":"publisher","unstructured":"Fu, T.J., Wang, W.Y., McDuff, D., Song, Y.: Doc2 ppt: automatic presentation slides generation from scientific documents. In: Proceedings of the AAAI Conference on Artificial Intelligence 36(1), 634\u2013642, June 2022. https:\/\/doi.org\/10.1609\/aaai.v36i1.19943, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/19943","DOI":"10.1609\/aaai.v36i1.19943"},{"key":"19_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Advances in neural information processing systems 27 (2014)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"19_CR14","doi-asserted-by":"publisher","unstructured":"Guo, S., Jin, Z., Sun, F., Li, J., Li, Z., Shi, Y., Cao, N.: Vinci: an intelligent graphic design system for generating advertising posters. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. CHI \u201921. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3411764.3445117","DOI":"10.1145\/3411764.3445117"},{"key":"19_CR15","doi-asserted-by":"publisher","unstructured":"Gupta, K., Lazarow, J., Achille, A., Davis, L., Mahadevan, V., Shrivastava, A.: Layouttransformer: layout generation and completion with self-attention. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 984\u2013994 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00104","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"19_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 (2018)"},{"key":"19_CR17","unstructured":"Ho, J., et\u00a0al.: Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"19_CR18","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR19","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)"},{"issue":"8","key":"19_CR20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Huang, K., Wang, Y., Zhou, Z., Ding, T., Gao, S., Ma, Y.: Learning to parse wireframes in images of man-made environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 626\u2013635 (2018)","DOI":"10.1109\/CVPR.2018.00072"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Inoue, N., Kikuchi, K., Simo-Serra, E., Otani, M., Yamaguchi, K.: Layoutdm: Discrete diffusion model for controllable layout generation (2023)","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"19_CR23","unstructured":"Jyothi, A.A., Durand, T., He, J., Sigal, L., Mori, G.: Layoutvae: Stochastic scene layout generation from a label set (2021)"},{"key":"19_CR24","doi-asserted-by":"publisher","unstructured":"Kikuchi, K., Simo-Serra, E., Otani, M., Yamaguchi, K.: Constrained graphic layout generation via latent optimization. In: ACM International Conference on Multimedia, pp. 88\u201396. MM \u201921 (2021). https:\/\/doi.org\/10.1145\/3474085.3475497","DOI":"10.1145\/3474085.3475497"},{"key":"19_CR25","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2013)"},{"key":"19_CR26","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2022)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Kong, X., Jiang, L., Chang, H., Zhang, H., Hao, Y., Gong, H., Essa, I.: Blt: Bidirectional layout transformer for controllable layout generation. arXiv preprint arXiv:2112.05112 (2021)","DOI":"10.1007\/978-3-031-19790-1_29"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Jiang, L., Essa, I., Le, P.B., Gong, H., Yang, M.H., Yang, W.: Neural design network: Graphic layout generation with constraints (2020)","DOI":"10.1007\/978-3-030-58580-8_29"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Levi, E., Brosh, E., Mykhailych, M., Perez, M.: Dlt: Conditioned layout generation with joint discrete-continuous diffusion layout transformer. arXiv preprint arXiv:2303.03755 (2023)","DOI":"10.1109\/ICCV51070.2023.00201"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"19_CR31","unstructured":"Li, J., Yang, J., Hertzmann, A., Zhang, J., Xu, T.: Layoutgan: generating graphic layouts with wireframe discriminators (2019)"},{"key":"19_CR32","unstructured":"Lin, J., Guo, J., Sun, S., Yang, Z.J., Lou, J.G., Zhang, D.: Layoutprompter: awaken the design ability of large language models. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context (2015)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Nauata, N., Chang, K.H., Cheng, C.Y., Mori, G., Furukawa, Y.: House-gan: Relational generative adversarial networks for graph-constrained house layout generation. In: European Conference on Computer Vision, pp. 162\u2013177. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_10"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Nauata, N., Hosseini, S., Chang, K.H., Chu, H., Cheng, C.Y., Furukawa, Y.: House-gan++: generative adversarial layout refinement network towards intelligent computational agent for professional architects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13632\u201313641 (2021)","DOI":"10.1109\/CVPR46437.2021.01342"},{"key":"19_CR36","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv preprint arXiv:2212.09748 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"19_CR38","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":"19_CR39","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: MICCAI, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Shabani, M.A., Hosseini, S., Furukawa, Y.: Housediffusion: vector floorplan generation via a diffusion model with discrete and continuous denoising (2022)","DOI":"10.1109\/CVPR52729.2023.00529"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Shabani, M.A., Hosseini, S., Furukawa, Y.: Housediffusion: vector floorplan generation via a diffusion model with discrete and continuous denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5466\u20135475 (2023)","DOI":"10.1109\/CVPR52729.2023.00529"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Shue, J.R., Chan, E.R., Po, R., Ankner, Z., Wu, J., Wetzstein, G.: 3d neural field generation using triplane diffusion. arXiv preprint arXiv:2211.16677 (2022)","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Singh, J., Zheng, L., Smith, C., Echevarria, J.: Paint2pix: interactive painting based progressive image synthesis and editing (2022)","DOI":"10.1007\/978-3-031-19781-9_39"},{"key":"19_CR44","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2022)"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Sudderth, E.B., Torralba, A., Freeman, W.T., Willsky, A.S.: Learning hierarchical models of scenes, objects, and parts. In: ICCV, vol.\u00a02 (2005)","DOI":"10.1109\/ICCV.2005.137"},{"key":"19_CR46","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31(1), February 2017. https:\/\/doi.org\/10.1609\/aaai.v31i1.11231, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/11231","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"19_CR47","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need (2017)"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Aesthetic text logo synthesis via content-aware layout inferring (2022)","DOI":"10.1109\/CVPR52688.2022.00247"},{"key":"19_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/3-540-45054-8_2","volume-title":"Computer Vision - ECCV 2000","author":"M Weber","year":"2000","unstructured":"Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18\u201332. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-45054-8_2"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, X., Xiaotian\u00a0Qiao, Y.C., Lau, R.W.: Content-aware generative modeling of graphic design layouts. ACM Trans. Graph. (Proc. of SIGGRAPH 2019) 38 (2019)","DOI":"10.1145\/3306346.3322971"},{"key":"19_CR51","doi-asserted-by":"publisher","unstructured":"Yamaguchi, K.: Canvasvae: learning to generate vector graphic documents. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5461\u20135469 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00543","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"19_CR52","doi-asserted-by":"publisher","unstructured":"Yang, X., Mei, T., Xu, Y.Q., Rui, Y., Li, S.: Automatic generation of visual-textual presentation layout. ACM Trans. Multimed. Comput. Commun. Appl. 12, 1\u201322 (2016). https:\/\/doi.org\/10.1145\/2818709","DOI":"10.1145\/2818709"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, J., Guo, J., Sun, S., Lou, J.G., Zhang, D.: Layoutdiffusion: improving graphic layout generation by discrete diffusion probabilistic models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00664"},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"19_CR55","doi-asserted-by":"publisher","unstructured":"Zheng, X., Qiao, X., Cao, Y., Lau, R.W.H.: Content-aware generative modeling of graphic design layouts. ACM Trans. Graph. 38(4) (2019). https:\/\/doi.org\/10.1145\/3306346.3322971. https:\/\/doi.org\/10.1145\/3306346.3322971","DOI":"10.1145\/3306346.3322971"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: Publaynet: largest dataset ever for document layout analysis (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"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\/978-3-031-72983-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T10:01:08Z","timestamp":1730109668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72983-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031729829","9783031729836"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72983-6_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}