{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T03:23:02Z","timestamp":1768706582395,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":57,"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":[{"name":"National Key R&D Program of China","award":["2022ZD0160801"],"award-info":[{"award-number":["2022ZD0160801"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023B1515120026, 2023B0303000016"],"award-info":[{"award-number":["2023B1515120026, 2023B0303000016"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172416, U22B2034, U21A20515"],"award-info":[{"award-number":["62172416, U22B2034, U21A20515"]}],"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\/3680528.3687633","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":4,"title":["InstanceTex: Instance-level Controllable Texture Synthesis for 3D Scenes via Diffusion Priors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1744-5607","authenticated-orcid":false,"given":"Mingxin","family":"Yang","sequence":"first","affiliation":[{"name":"Shenzhen VisuCA Key Lab, SIAT, CAS, and University of Chinese Academy of Sciences, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3376-1725","authenticated-orcid":false,"given":"Jianwei","family":"Guo","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8293-0417","authenticated-orcid":false,"given":"Yuzhi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0689-7463","authenticated-orcid":false,"given":"Lan","family":"Chen","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1060-689X","authenticated-orcid":false,"given":"Pu","family":"Li","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy Of Sciences, and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3360-2679","authenticated-orcid":false,"given":"Zhanglin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shenzhen VisuCA Key Lab, SIAT, CAS, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0092-6474","authenticated-orcid":false,"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy Of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3212-0544","authenticated-orcid":false,"given":"Hui","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_2_2_1","volume-title":"SketchFab. The best 3d viewer on the web","year":"2022","unstructured":"2022. SketchFab. The best 3d viewer on the web. https:\/\/sketchfab.com\/"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Sai Bi Nima\u00a0Khademi Kalantari and Ravi Ramamoorthi. 2017. Patch-based optimization for image-based texture mapping. ACM Trans. Graph. 36 4 (2017) 106:1\u2013106:11.","DOI":"10.1145\/3072959.3073610"},{"key":"e_1_3_3_2_5_1","volume-title":"International Conference on Learning Representations","author":"Bi\u0144kowski Miko\u0142aj","year":"2018","unstructured":"Miko\u0142aj Bi\u0144kowski, Dougal\u00a0J. Sutherland, Michael Arbel, and Arthur Gretton. 2018. Demystifying MMD GANs. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00819"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"e_1_3_3_2_8_1","unstructured":"Angel\u00a0X Chang Thomas Funkhouser Leonidas Guibas Pat Hanrahan Qixing Huang Zimo Li Silvio Savarese Manolis Savva Shuran Song Hao Su et\u00a0al. 2015. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1512.03012 (2015)."},{"key":"e_1_3_3_2_9_1","unstructured":"Ziyi Chang George\u00a0A Koulieris and Hubert\u00a0PH Shum. 2023. On the Design Fundamentals of Diffusion Models: A Survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.04542 (2023)."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01992"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618201"},{"key":"e_1_3_3_2_13_1","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems 34 (2021) 8780\u20138794."},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Aysegul Dundar Jun Gao Andrew Tao and Bryan Catanzaro. 2023. Fine detailed texture learning for 3d meshes with generative models. IEEE Trans. Pattern Anal. Mach. Intell. (2023).","DOI":"10.1109\/TPAMI.2023.3319429"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00488"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Ran Gal Yonatan Wexler Eyal Ofek Hugues Hoppe and Daniel Cohen-Or. 2010. Seamless montage for texturing models. Comp. Graph. Forum 29 2 (2010) 479\u2013486.","DOI":"10.1111\/j.1467-8659.2009.01617.x"},{"key":"e_1_3_3_2_18_1","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. Advances in Neural Information Processing Systems 35 (2022) 31841\u201331854."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Lin Gao Tong Wu Yu-Jie Yuan Ming-Xian Lin Yu-Kun Lai and Hao Zhang. 2021. Tm-net: Deep generative networks for textured meshes. ACM Trans. Graph. 40 6 (2021) 1\u201315.","DOI":"10.1145\/3478513.3480503"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00111"},{"key":"e_1_3_3_2_21_1","first-page":"85","volume-title":"Eurographics Symposium on Rendering","author":"Hasselgren Jon","year":"2021","unstructured":"Jon Hasselgren, Jacob Munkberg, Jaakko Lehtinen, Miika Aittala, and Samuli Laine. 2021. Appearance-Driven Automatic 3D Model Simplification. In Eurographics Symposium on Rendering. 85\u201397."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_3_2_23_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28024"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Tom Kelly Paul Guerrero Anthony Steed Peter Wonka and Niloy\u00a0J Mitra. 2018. FrankenGAN: guided detail synthesis for building mass-models using style-synchonized GANs. ACM Trans. Graph. 37 6 (2018) 14\u00a0pages.","DOI":"10.1145\/3272127.3275065"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Julian Knodt Zherong Pan Kui Wu and Xifeng Gao. 2023. Joint UV Optimization and Texture Baking. ACM Trans. Graph. 43 1 Article 2 (2023) 20\u00a0pages.","DOI":"10.1145\/3617683"},{"key":"e_1_3_3_2_27_1","unstructured":"Chenghao Li Chaoning Zhang Atish Waghwase Lik-Hang Lee Francois Rameau Yang Yang Sung-Ho Bae and Choong\u00a0Seon Hong. 2023. Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.06131 (2023)."},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_3_2_30_1","unstructured":"Yuxin Liu Minshan Xie Hanyuan Liu and Tien-Tsin Wong. 2023b. Text-Guided Texturing by Synchronized Multi-View Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.12891 (2023)."},{"key":"e_1_3_3_2_31_1","unstructured":"Fan Lu Kwan-Yee Lin Yan Xu Hongsheng Li Guang Chen and Changjun Jiang. 2024. Urban Architect: Steerable 3D Urban Scene Generation with Layout Prior. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.06780 (2024)."},{"key":"e_1_3_3_2_32_1","unstructured":"Oscar Alejandro\u00a0Mendez Maldonado Simon Hadfield Nicolas Pugeault and R. Bowden. 2016. Next-Best Stereo: Extending Next-Best View Optimisation For Collaborative Sensors. Proc. BMVC (2016) 1\u201312."},{"key":"e_1_3_3_2_33_1","unstructured":"Meshy. 2023. Meshy \u2013 3d ai generator.https:\/\/www.meshy.ai\/"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"e_1_3_3_2_37_1","first-page":"16784","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Nichol Alexander\u00a0Quinn","year":"2022","unstructured":"Alexander\u00a0Quinn 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. In Proceedings of the 39th International Conference on Machine Learning. PMLR, 16784\u201316804."},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00463"},{"key":"e_1_3_3_2_39_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_2_40_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 1 2 (2022) 3."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_43_1","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan Tim Salimans et\u00a0al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems 35 (2022) 36479\u201336494."},{"key":"e_1_3_3_2_44_1","unstructured":"Zifan Shi Sida Peng Yinghao Xu Yiyi Liao and Yujun Shen. 2022. Deep generative models on 3d representations: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.15663 (2022)."},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_5"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Neil Smith Nils Moehrle Michael Goesele and Wolfgang Heidrich. 2018. Aerial Path Planning for Urban Scene Reconstruction: A Continuous Optimization Method and Benchmark. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 37 6 (2018) 183:1\u2013183:15.","DOI":"10.1145\/3272127.3275010"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611800"},{"key":"e_1_3_3_2_48_1","unstructured":"Ashkan Taghipour Morteza Ghahremani Mohammed Bennamoun Aref\u00a0Miri Rekavandi Hamid Laga and Farid Boussaid. 2024. Box It to Bind It: Unified Layout Control and Attribute Binding in T2I Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17910 (2024)."},{"key":"e_1_3_3_2_49_1","unstructured":"Jiaxiang Tang Jiawei Ren Hang Zhou Ziwei Liu and Gang Zeng. 2023. Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16653 (2023)."},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_54"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"crossref","unstructured":"Weidan Xiong Hongqian Zhang Botao Peng Ziyu Hu Yongli Wu Jianwei Guo and Hui Huang. 2023. TwinTex: Geometry-Aware Texture Generation for Abstracted 3D Architectural Models. ACM Trans. Graph. 42 6 (2023) 1\u201314.","DOI":"10.1145\/3618328"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00388"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13656"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Guangyao Zhai Evin\u00a0P\u0131nar \u00d6rnek Dave\u00a0Zhenyu Chen Ruotong Liao Yan Di Nassir Navab Federico Tombari and Benjamin Busam. 2024. EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion. ECCV (2024).","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"crossref","unstructured":"Qian-Yi Zhou and Vladlen Koltun. 2014. Color map optimization for 3D reconstruction with consumer depth cameras. ACM Trans. Graph. 33 4 (2014) 155:1\u2013155:10.","DOI":"10.1145\/2601097.2601134"}],"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\/3680528.3687633","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:27Z","timestamp":1750294707000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687633"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":57,"alternative-id":["10.1145\/3680528.3687633","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687633","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"}}]}}