{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T01:45:01Z","timestamp":1778809501682,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733343","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"1617-1625","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Floorplan-Diffusion: Automatic Floor Plan Generation via Pre-trained Large Latent Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3616-5058","authenticated-orcid":false,"given":"Minyang","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2386-0017","authenticated-orcid":false,"given":"Yunzhong","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4782-7261","authenticated-orcid":false,"given":"Xiang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5538-7367","authenticated-orcid":false,"given":"Xiangdong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0926-5805(00)00099-6"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461977"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"e_1_3_2_1_4_1","volume-title":"LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation. arXiv preprint arXiv (Feb","author":"Cheng Jiaxin","year":"2023","unstructured":"Jiaxin Cheng, Xiao Liang, Xingjian Shi, Tong He, Tianjun Xiao, and Mu Li. 2023. LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation. arXiv preprint arXiv (Feb 2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"Jiaxin Cheng Xiao Liang Xingjian Shi Tong He Tianjun Xiao and Mu Li. 2023. LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation. arXiv:2302.08908 [cs.CV] https:\/\/arxiv.org\/abs\/2302.08908"},{"key":"e_1_3_2_1_6_1","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik AmitH Bermano Gal Chechik and Daniel Cohen-Or. [n. d.]. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. ([n. d.])."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680681"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392391"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_11_1","volume-title":"Kingma and Max Welling","author":"P.","year":"2013","unstructured":"DiederikP. Kingma and Max Welling. 2013. Auto-Encoding Variational Bayes. arXiv: Machine Learning,arXiv: Machine Learning (Dec 2013)."},{"key":"e_1_3_2_1_12_1","volume-title":"GRAINS: Generative Recursive Autoencoders for INdoor Scenes. ACM Transactions on Graphics,ACM Transactions on Graphics (Jul","author":"Li Manyi","year":"2018","unstructured":"Manyi Li, AkshayGadi Patil, Kai Xu, Siddhartha Chaudhuri, Owais Khan, Ariel Shamir, Changhe Tu, Baoquan Chen, Daniel Cohen-Or, and Hao Zhang. 2018. GRAINS: Generative Recursive Autoencoders for INdoor Scenes. ACM Transactions on Graphics,ACM Transactions on Graphics (Jul 2018)."},{"key":"e_1_3_2_1_13_1","unstructured":"Luping Liu Yi Ren Zhijie Lin and Zhou Zhao. [n. d.]. Pseudo Numerical Methods for Diffusion Models on Manifolds. ([n. d.])."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1882261.1866203"},{"key":"e_1_3_2_1_15_1","unstructured":"Nelson Nauata Sepidehsadat Hosseini Kai-Hung Chang Hang Chu Chin-Yi Cheng and Yasutaka Furukawa. 2021. House-GAN: Generative Adversarial Layout Refinement Networks. arXiv:2103.02574 [cs.CV] https:\/\/arxiv.org\/abs\/2103.02574"},{"key":"e_1_3_2_1_16_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv:2112.10741 [cs.CV] https:\/\/arxiv.org\/abs\/2112.10741","author":"Nichol Alex","year":"2022","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv:2112.10741 [cs.CV] https:\/\/arxiv.org\/abs\/2112.10741"},{"key":"e_1_3_2_1_17_1","volume-title":"Neural Discrete Representation Learning","author":"Oord Aaronvanden","year":"2017","unstructured":"Aaronvanden Oord, Oriol Vinyals, and Koray Kavukcuoglu. 2017. Neural Discrete Representation Learning. Cornell University - arXiv,Cornell University - arXiv (Nov 2017)."},{"key":"e_1_3_2_1_18_1","unstructured":"Kushagra Pandey Avideep Mukherjee Piyush Rai and Abhishek Kumar. 2022. DiffuseVAE: Efficient Controllable and High-Fidelity Generation from Low-Dimensional Latents. (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00662"},{"key":"e_1_3_2_1_20_1","unstructured":"Aditya Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. arXiv:2102.12092 [cs.CV] https:\/\/arxiv.org\/abs\/2102.12092"},{"key":"e_1_3_2_1_21_1","volume-title":"On the Convergence of Adam and Beyond. International Conference on Learning Representations, International Conference on Learning Representations (Feb","author":"Reddi J.","year":"2018","unstructured":"SashankJ. Reddi, Satyen Kale, and Sanjiv Kumar. 2018. On the Convergence of Adam and Beyond. International Conference on Learning Representations, International Conference on Learning Representations (Feb 2018)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.91"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2013.01.001"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2013.01.003"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2017.1313980"},{"key":"e_1_3_2_1_27_1","volume-title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. (Aug","author":"Ruiz Nataniel","year":"2022","unstructured":"Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2022. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. (Aug 2022)."},{"key":"e_1_3_2_1_28_1","unstructured":"Mohammad Amin Shabani Sepidehsadat Hosseini and Yasutaka Furukawa. HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising."},{"key":"e_1_3_2_1_29_1","volume-title":"Make-A-Video: Text-to-Video Generation without Text-Video Data. (Sep","author":"Singer Uriel","year":"2022","unstructured":"Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, and Yaniv Taigman. 2022. Make-A-Video: Text-to-Video Generation without Text-Video Data. (Sep 2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"Denoising Diffusion Implicit Models. arXiv: Learning,arXiv: Learning (Oct","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. arXiv: Learning,arXiv: Learning (Oct 2020)."},{"key":"e_1_3_2_1_31_1","unstructured":"Wei Sun and Tianfu Wu. 2019. Image Synthesis From Reconfigurable Layout and Style. arXiv:1908.07500 [cs.CV] https:\/\/arxiv.org\/abs\/1908.07500"},{"key":"e_1_3_2_1_32_1","volume-title":"NVAE: A Deep Hierarchical Variational Autoencoder. Neural Information Processing Systems,Neural Information Processing Systems (Jul","author":"Vahdat Arash","year":"2020","unstructured":"Arash Vahdat and Jan Kautz. 2020. NVAE: A Deep Hierarchical Variational Autoencoder. Neural Information Processing Systems,Neural Information Processing Systems (Jul 2020)."},{"key":"e_1_3_2_1_33_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arXiv:1706.03762 [cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356556"},{"key":"e_1_3_2_1_35_1","volume-title":"ACM Transactions on Graphics (Aug","author":"Zhang Zaiwei","year":"2018","unstructured":"Zaiwei Zhang, Zhan-Ying Yang, Chongyang Ma, Linjie Luo, AlexanderG. Huth, Etienne Vouga, and Qixing Huang. 2018. Deep Generative Modeling for Scene Synthesis via Hybrid Representations. ACM Transactions on Graphics, ACM Transactions on Graphics (Aug 2018)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.244"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:13:28Z","timestamp":1755749608000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"alternative-id":["10.1145\/3731715.3733343","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733343","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}