{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:08:20Z","timestamp":1784268500963,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322113, 62376156"],"award-info":[{"award-number":["62322113, 62376156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687672","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4649-0565","authenticated-orcid":false,"given":"Han","family":"Yan","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2517-087X","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6021-7207","authenticated-orcid":false,"given":"Zhennan","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8314-7782","authenticated-orcid":false,"given":"Shenzhou","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5409-1097","authenticated-orcid":false,"given":"Weixuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9402-6919","authenticated-orcid":false,"given":"Taizhang","family":"Shang","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3653-4165","authenticated-orcid":false,"given":"Weizhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5250-1437","authenticated-orcid":false,"given":"Tian","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9181-5174","authenticated-orcid":false,"given":"Xiaqiang","family":"Dai","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-2845","authenticated-orcid":false,"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4125-1554","authenticated-orcid":false,"given":"Hongdong","family":"Li","sequence":"additional","affiliation":[{"name":"Australian National University, Canberra, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6213-554X","authenticated-orcid":false,"given":"Pan","family":"Ji","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00659"},{"key":"e_1_3_3_1_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14020"},{"key":"e_1_3_3_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"e_1_3_3_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02018"},{"key":"e_1_3_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"e_1_3_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14989"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"e_1_3_3_1_9_1","doi-asserted-by":"crossref","unstructured":"Junting Dong Qi Fang Zehuan Huang Xudong Xu Jingbo Wang Sida Peng and Bo Dai. 2024. TELA: Text to Layer-wise 3D Clothed Human Generation. arXiv:https:\/\/arXiv.org\/abs\/2404.16748 (2024).","DOI":"10.1007\/978-3-031-72698-9_2"},{"key":"e_1_3_3_1_10_1","doi-asserted-by":"crossref","unstructured":"David\u00a0H Douglas and Thomas\u00a0K Peucker. 1973. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica (1973).","DOI":"10.3138\/FM57-6770-U75U-7727"},{"key":"e_1_3_3_1_11_1","unstructured":"David Eberly. 2008. Triangulation by ear clipping. Geometric Tools (2008)."},{"key":"e_1_3_3_1_12_1","unstructured":"Dave Epstein Ben Poole Ben Mildenhall Alexei\u00a0A Efros and Aleksander Holynski. 2024. Disentangled 3D Scene Generation with Layout Learning. arXiv:https:\/\/arXiv.org\/abs\/2402.16936 (2024)."},{"key":"e_1_3_3_1_13_1","unstructured":"Chuan Fang Xiaotao Hu Kunming Luo and Ping Tan. 2023. Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints. arXiv:https:\/\/arXiv.org\/abs\/2310.03602 (2023)."},{"key":"e_1_3_3_1_14_1","unstructured":"Yao Feng Weiyang Liu Timo Bolkart Jinlong Yang Marc Pollefeys and Michael\u00a0J Black. 2023. Learning disentangled avatars with hybrid 3d representations. arXiv:https:\/\/arXiv.org\/abs\/2309.06441 (2023)."},{"key":"e_1_3_3_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"e_1_3_3_1_16_1","unstructured":"Huan Fu Rongfei Jia Lin Gao Mingming Gong Binqiang Zhao Steve Maybank and Dacheng Tao. 2021b. 3d-future: 3d furniture shape with texture. IJCV (2021)."},{"key":"e_1_3_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"e_1_3_3_1_18_1","volume-title":"NeurIPS","author":"Gao Jun","year":"2022","unstructured":"Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, and Sanja Fidler. 2022. GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images. In NeurIPS."},{"key":"e_1_3_3_1_19_1","unstructured":"Anchit Gupta Wenhan Xiong Yixin Nie Ian Jones and Barlas O\u011fuz. 2023. 3dgen: Triplane latent diffusion for textured mesh generation. arXiv:https:\/\/arXiv.org\/abs\/2303.05371 (2023)."},{"key":"e_1_3_3_1_20_1","volume-title":"NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In NeurIPS."},{"key":"e_1_3_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"e_1_3_3_1_22_1","unstructured":"Yicong Hong Kai Zhang Jiuxiang Gu Sai Bi Yang Zhou Difan Liu Feng Liu Kalyan Sunkavalli Trung Bui and Hao Tan. 2023. Lrm: Large reconstruction model for single image to 3d. arXiv:https:\/\/arXiv.org\/abs\/2311.04400 (2023)."},{"key":"e_1_3_3_1_23_1","unstructured":"Shoukang Hu Fangzhou Hong Tao Hu Liang Pan Haiyi Mei Weiye Xiao Lei Yang and Ziwei Liu. 2023. Humanliff: Layer-wise 3d human generation with diffusion model. arXiv:https:\/\/arXiv.org\/abs\/2308.09712 (2023)."},{"key":"e_1_3_3_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"e_1_3_3_1_25_1","unstructured":"Manyi Li Akshay\u00a0Gadi Patil Kai Xu Siddhartha Chaudhuri Owais Khan Ariel Shamir Changhe Tu Baoquan Chen Daniel Cohen-Or and Hao Zhang. 2019. Grains: Generative recursive autoencoders for indoor scenes. ACM TOG (2019)."},{"key":"e_1_3_3_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"e_1_3_3_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00150"},{"key":"e_1_3_3_1_28_1","unstructured":"Yuxin Liu Minshan Xie Hanyuan Liu and Tien-Tsin Wong. 2023. Text-guided texturing by synchronized multi-view diffusion. arXiv:https:\/\/arXiv.org\/abs\/2311.12891 (2023)."},{"key":"e_1_3_3_1_29_1","doi-asserted-by":"crossref","unstructured":"Matthew Loper Naureen Mahmood Javier Romero Gerard Pons-Moll and Michael\u00a0J. Black. 2015. SMPL: A Skinned Multi-Person Linear Model. SIGGRAPH Asia (2015).","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_10"},{"key":"e_1_3_3_1_32_1","volume-title":"NeurIPS","author":"Paschalidou Despoina","year":"2021","unstructured":"Despoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis, Andreas Geiger, and Sanja Fidler. 2021. Atiss: Autoregressive transformers for indoor scene synthesis. In NeurIPS."},{"key":"e_1_3_3_1_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14927"},{"key":"e_1_3_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_1_35_1","unstructured":"Ryan Po and Gordon Wetzstein. 2023. Compositional 3d scene generation using locally conditioned diffusion. arXiv:https:\/\/arXiv.org\/abs\/2303.12218 (2023)."},{"key":"e_1_3_3_1_36_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv:https:\/\/arXiv.org\/abs\/2209.14988 (2022)."},{"key":"e_1_3_3_1_37_1","unstructured":"Guocheng Qian Jinjie Mai Abdullah Hamdi Jian Ren Aliaksandr Siarohin Bing Li Hsin-Ying Lee Ivan Skorokhodov Peter Wonka Sergey Tulyakov et\u00a0al. 2023. Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors. arXiv:https:\/\/arXiv.org\/abs\/2306.17843 (2023)."},{"key":"e_1_3_3_1_38_1","doi-asserted-by":"crossref","unstructured":"Urs Ramer. 1972. An iterative procedure for the polygonal approximation of plane curves. CGIP (1972).","DOI":"10.1016\/S0146-664X(72)80017-0"},{"key":"e_1_3_3_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"e_1_3_3_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"e_1_3_3_1_42_1","doi-asserted-by":"crossref","unstructured":"Jonas Schult Sam Tsai Lukas H\u00f6llein Bichen Wu Jialiang Wang Chih-Yao Ma Kunpeng Li Xiaofang Wang Felix Wimbauer Zijian He Peizhao Zhang Bastian Leibe Peter Vajda and Ji Hou. 2023b. ControlRoom3D: Room Generation using Semantic Proxy Rooms. arXiv:https:\/\/arXiv.org\/abs\/2312.05208 (2023).","DOI":"10.1109\/CVPR52733.2024.00593"},{"key":"e_1_3_3_1_43_1","unstructured":"Ruoxi Shi Hansheng Chen Zhuoyang Zhang Minghua Liu Chao Xu Xinyue Wei Linghao Chen Chong Zeng and Hao Su. 2023. Zero123++: a single image to consistent multi-view diffusion base model. arXiv:https:\/\/arXiv.org\/abs\/2310.15110 (2023)."},{"key":"e_1_3_3_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"e_1_3_3_1_45_1","volume-title":"ICML","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In ICML. https:\/\/dl.acm.org\/doi\/10.5555\/3045118.3045358"},{"key":"e_1_3_3_1_46_1","unstructured":"Jiapeng Tang Yinyu Nie Lev Markhasin Angela Dai Justus Thies and Matthias Nie\u00dfner. 2023. Diffuscene: Scene graph denoising diffusion probabilistic model for generative indoor scene synthesis. arXiv:https:\/\/arXiv.org\/abs\/2303.14207 (2023)."},{"key":"e_1_3_3_1_47_1","doi-asserted-by":"crossref","unstructured":"Stefan Van\u00a0der Walt Johannes\u00a0L Sch\u00f6nberger Juan Nunez-Iglesias Fran\u00e7ois Boulogne Joshua\u00a0D Warner Neil Yager Emmanuelle Gouillart and Tony Yu. 2014. scikit-image: image processing in Python. PeerJ (2014).","DOI":"10.7287\/peerj.preprints.336v1"},{"key":"e_1_3_3_1_48_1","volume-title":"NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS. https:\/\/dl.acm.org\/doi\/10.5555\/3295222.3295349"},{"key":"e_1_3_3_1_49_1","unstructured":"Jionghao Wang Yuan Liu Zhiyang Dou Zhengming Yu Yongqing Liang Xin Li Wenping Wang Rong Xie and Li Song. 2023a. Disentangled Clothed Avatar Generation from Text Descriptions. arXiv:https:\/\/arXiv.org\/abs\/2312.05295 (2023)."},{"key":"e_1_3_3_1_50_1","doi-asserted-by":"crossref","unstructured":"Kai Wang Yu-An Lin Ben Weissmann Manolis Savva Angel\u00a0X Chang and Daniel Ritchie. 2019. Planit: Planning and instantiating indoor scenes with relation graph and spatial prior networks. ACM TOG (2019).","DOI":"10.1145\/3306346.3322941"},{"key":"e_1_3_3_1_51_1","doi-asserted-by":"crossref","unstructured":"Kai Wang Manolis Savva Angel\u00a0X Chang and Daniel Ritchie. 2018. Deep convolutional priors for indoor scene synthesis. ACM TOG (2018).","DOI":"10.1145\/3197517.3201362"},{"key":"e_1_3_3_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"e_1_3_3_1_53_1","doi-asserted-by":"crossref","unstructured":"Yi Wang Jian Ma Ruizhi Shao Qiao Feng Yu-Kun Lai Yebin Liu and Kun Li. 2023b. HumanCoser: Layered 3D Human Generation via Semantic-Aware Diffusion Model. arXiv:https:\/\/arXiv.org\/abs\/2312.05804 (2023).","DOI":"10.1109\/ISMAR62088.2024.00058"},{"key":"e_1_3_3_1_54_1","unstructured":"Zehao Wen Zichen Liu Srinath Sridhar and Rao Fu. 2023. AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes. arXiv:https:\/\/arXiv.org\/abs\/2312.06644 (2023)."},{"key":"e_1_3_3_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_12"},{"key":"e_1_3_3_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01989"},{"key":"e_1_3_3_1_57_1","unstructured":"Zhennan Wu Yang Li Han Yan Taizhang Shang Weixuan Sun Senbo Wang Ruikai Cui Weizhe Liu Hiroyuki Sato Hongdong Li and Pan Ji. 2024. BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation. arXiv:https:\/\/arXiv.org\/abs\/2401.17053 (2024)."},{"key":"e_1_3_3_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00301"},{"key":"e_1_3_3_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"e_1_3_3_1_60_1","unstructured":"Guangyao Zhai Evin\u00a0Pinar \u00d6rnek Shun-Cheng Wu Yan Di Federico Tombari Nassir Navab and Benjamin Busam. 2023. CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graphs. arXiv:https:\/\/arXiv.org\/abs\/2305.16283 (2023)."},{"key":"e_1_3_3_1_61_1","unstructured":"Qihang Zhang Chaoyang Wang Aliaksandr Siarohin Peiye Zhuang Yinghao Xu Ceyuan Yang Dahua Lin Bolei Zhou Sergey Tulyakov and Hsin-Ying Lee. 2023. Scenewiz3d: Towards text-guided 3d scene composition. arXiv:https:\/\/arXiv.org\/abs\/2312.08885 (2023)."},{"key":"e_1_3_3_1_62_1","doi-asserted-by":"crossref","unstructured":"Xin-Yang Zheng Hao Pan Peng-Shuai Wang Xin Tong Yang Liu and Heung-Yeung Shum. 2023. Locally attentional sdf diffusion for controllable 3d shape generation. arXiv:https:\/\/arXiv.org\/abs\/2305.04461 (2023).","DOI":"10.1145\/3592103"},{"key":"e_1_3_3_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"e_1_3_3_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00748"}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Conference Papers","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687672","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:20Z","timestamp":1750295900000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":63,"alternative-id":["10.1145\/3680528.3687672","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687672","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}