{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:27:05Z","timestamp":1742956025897,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031500718"},{"type":"electronic","value":"9783031500725"}],"license":[{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-50072-5_35","type":"book-chapter","created":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T08:02:17Z","timestamp":1703750537000},"page":"441-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion-Based Semantic Image Synthesis from\u00a0Sparse Layouts"],"prefix":"10.1007","author":[{"given":"Yuantian","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Iizuka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Fukui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Ashual, O., Wolf, L.: Specifying object attributes and relations in interactive scene generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2019","key":"35_CR1","DOI":"10.1109\/ICCV.2019.00466"},{"doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1511\u20131520 (2017)","key":"35_CR2","DOI":"10.1109\/ICCV.2017.168"},{"doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789\u20138797 (2018)","key":"35_CR3","DOI":"10.1109\/CVPR.2018.00916"},{"unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems 34, pp. 8780\u20138794 (2021)","key":"35_CR4"},{"doi-asserted-by":"crossref","unstructured":"Gao, C., Liu, Q., Xu, Q., Wang, L., Liu, J., Zou, C.: SketchyCOCO: image generation from freehand scene sketches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5174\u20135183 (2020)","key":"35_CR5","DOI":"10.1109\/CVPR42600.2020.00522"},{"doi-asserted-by":"crossref","unstructured":"Ghosh, A., et al.: Interactive sketch & fill: multiclass sketch-to-image translation. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","key":"35_CR6","DOI":"10.1109\/ICCV.2019.00126"},{"unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks (2014)","key":"35_CR7"},{"issue":"2","key":"35_CR8","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/arts7020018","volume":"7","author":"A Hertzmann","year":"2018","unstructured":"Hertzmann, A.: Can computers create art? Arts 7(2), 18 (2018)","journal-title":"Arts"},{"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: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)","key":"35_CR9"},{"unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)","key":"35_CR10"},{"unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems 33, pp. 6840\u20136851 (2020)","key":"35_CR11"},{"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, pp. 1125\u20131134 (2017)","key":"35_CR12","DOI":"10.1109\/CVPR.2017.632"},{"doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","key":"35_CR13","DOI":"10.1109\/CVPR.2018.00133"},{"doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, T., Malik, J.: Diverse image synthesis from semantic layouts via conditional IMLE. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4220\u20134229 (2019)","key":"35_CR14","DOI":"10.1109\/ICCV.2019.00432"},{"issue":"11","key":"35_CR15","doi-asserted-by":"publisher","first-page":"3577","DOI":"10.1007\/s00371-021-02188-1","volume":"38","author":"L Li","year":"2022","unstructured":"Li, L., Tang, J., Shao, Z., Tan, X., Ma, L.: Sketch-to-photo face generation based on semantic consistency preserving and similar connected component refinement. Vis. Comput. 38(11), 3577\u20133594 (2022)","journal-title":"Vis. Comput."},{"unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)","key":"35_CR16"},{"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, pp. 2337\u20132346 (2019)","key":"35_CR17","DOI":"10.1109\/CVPR.2019.00244"},{"doi-asserted-by":"crossref","unstructured":"Qi, X., Chen, Q., Jia, J., Koltun, V.: Semi-parametric image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8808\u20138816 (2018)","key":"35_CR18","DOI":"10.1109\/CVPR.2018.00918"},{"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":"35_CR19"},{"unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)","key":"35_CR20"},{"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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695, June 2022","key":"35_CR21","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","key":"35_CR22","DOI":"10.1145\/3528233.3530757"},{"issue":"4","key":"35_CR23","first-page":"4713","volume":"45","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4713\u20134726 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (2022)","key":"35_CR24"},{"unstructured":"Sasaki, H., Willcocks, C.G., Breckon, T.P.: UNIT-DDPM: UNpaired image translation with denoising diffusion probabilistic models. arXiv preprint arXiv:2104.05358 (2021)","key":"35_CR25"},{"unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)","key":"35_CR26"},{"unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)","key":"35_CR27"},{"unstructured":"Sushko, V., Sch\u00f6nfeld, E., Zhang, D., Gall, J., Schiele, B., Khoreva, A.: You only need adversarial supervision for semantic image synthesis. arXiv preprint arXiv:2012.04781 (2020)","key":"35_CR28"},{"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, pp. 8798\u20138807 (2018)","key":"35_CR29","DOI":"10.1109\/CVPR.2018.00917"},{"unstructured":"Wang, W., et al.: Semantic image synthesis via diffusion models (2022)","key":"35_CR30"},{"doi-asserted-by":"publisher","unstructured":"Yu, Y., Li, D., Li, B., Li, N.: Multi-style image generation based on semantic image. Vis. Comput. 1\u201316 (2023). https:\/\/doi.org\/10.1007\/s00371-023-03042-2","key":"35_CR31","DOI":"10.1007\/s00371-023-03042-2"},{"doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 2017","key":"35_CR32","DOI":"10.1109\/ICCV.2017.629"},{"key":"35_CR33","doi-asserted-by":"publisher","first-page":"6309","DOI":"10.1007\/s00371-022-02731-8","volume":"39","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., et al.: Stroke-based semantic segmentation for scene-level free-hand sketches. Vis. Comput. 39, 6309\u20136321 (2022). https:\/\/doi.org\/10.1007\/s00371-022-02731-8","journal-title":"Vis. Comput."},{"doi-asserted-by":"crossref","unstructured":"Zhu, P., Abdal, R., Qin, Y., Wonka, P.: SEAN: image synthesis with semantic region-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5104\u20135113 (2020)","key":"35_CR34","DOI":"10.1109\/CVPR42600.2020.00515"},{"doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, Z., You, A., Bai, X.: Semantically multi-modal image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5467\u20135476 (2020)","key":"35_CR35","DOI":"10.1109\/CVPR42600.2020.00551"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-50072-5_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T08:09:41Z","timestamp":1703750981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-50072-5_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,29]]},"ISBN":["9783031500718","9783031500725"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-50072-5_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,29]]},"assertion":[{"value":"29 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"385","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"149","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}