{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:25:36Z","timestamp":1780392336074,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":87,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The InnoHK Program"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0904700"],"award-info":[{"award-number":["2023YFF0904700"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20020484222"],"award-info":[{"award-number":["20020484222"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276031"],"award-info":[{"award-number":["62276031"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680757","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"370-379","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3947-0570","authenticated-orcid":false,"given":"Zeyu","family":"Li","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4287-3809","authenticated-orcid":false,"given":"Ruitong","family":"Gan","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University & Centre for Artificial Intelligence and Robotics, HKISI_CAS, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4360-7035","authenticated-orcid":false,"given":"Chuanchen","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1579-2357","authenticated-orcid":false,"given":"Yuxi","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence and Robotics, HKISI_CAS, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5183-8538","authenticated-orcid":false,"given":"Jiaheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6189-8796","authenticated-orcid":false,"given":"Ziwei","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0023-0220","authenticated-orcid":false,"given":"Xucheng","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3043-2122","authenticated-orcid":false,"given":"Man","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of automation, Chinese Academy of Sciences & Centre for Artificial Intelligence and Robotics, HKISI_CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5276-0114","authenticated-orcid":false,"given":"Junran","family":"Peng","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00442"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on machine learning. PMLR, 40--49","author":"Achlioptas Panos","year":"2018","unstructured":"Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, and Leonidas Guibas. 2018. Learning representations and generative models for 3d point clouds. In International conference on machine learning. PMLR, 40--49."},{"key":"e_1_3_2_1_3_1","unstructured":"AmbientCG. 2024. Pbr repository. https:\/\/ambientcg.com."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00126"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.487"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462002"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"e_1_3_2_1_8_1","volume-title":"Benchmarking in manipulation research: The ycb object and model set and benchmarking protocols. arXiv preprint arXiv:1502.03143","author":"Calli Berk","year":"2015","unstructured":"Berk Calli, Aaron Walsman, Arjun Singh, Siddhartha Srinivasa, Pieter Abbeel, and Aaron M Dollar. 2015. Benchmarking in manipulation research: The ycb object and model set and benchmarking protocols. arXiv preprint arXiv:1502.03143 (2015)."},{"key":"e_1_3_2_1_9_1","volume-title":"MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignment. arXiv preprint arXiv:2404.02899","author":"Ceylan Duygu","year":"2024","unstructured":"Duygu Ceylan, Valentin Deschaintre, Thibault Groueix, Rosalie Martin, Chun-Hao Huang, Romain Rouffet, Vladimir Kim, and Ga\u00ebtan Lassagne. 2024. MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignment. arXiv preprint arXiv:2404.02899 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"e_1_3_2_1_12_1","volume-title":"Text2tex: Text-driven texture synthesis via diffusion models. arXiv preprint arXiv:2303.11396","author":"Chen Dave Zhenyu","year":"2023","unstructured":"Dave Zhenyu Chen, Yawar Siddiqui, Hsin-Ying Lee, Sergey Tulyakov, and Matthias Nie\u00dfner. 2023. Text2tex: Text-driven texture synthesis via diffusion models. arXiv preprint arXiv:2303.11396 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation. arXiv preprint arXiv:2303.13873","author":"Chen Rui","year":"2023","unstructured":"Rui Chen, Yongwei Chen, Ningxin Jiao, and Kui Jia. 2023. Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation. arXiv preprint arXiv:2303.13873 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"e_1_3_2_1_15_1","unstructured":"MMSegmentation Contributors. 2020. MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation."},{"key":"e_1_3_2_1_16_1","unstructured":"MMEngine Contributors. 2022. MMEngine: OpenMMLab Foundational Library for Training Deep Learning Models. https:\/\/github.com\/open-mmlab\/mmengine. (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Samir Yitzhak Gadre, et al","author":"Deitke Matt","year":"2023","unstructured":"Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, et al. 2023. Objaverse-xl: A universe of 10m 3d objects. arXiv preprint arXiv:2307.05663 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201378"},{"key":"e_1_3_2_1_20_1","volume-title":"Computer Graphics Forum","author":"Deschaintre Valentin","unstructured":"Valentin Deschaintre, George Drettakis, and Adrien Bousseau. 2020. Guided fine-tuning for large-scale material transfer. In Computer Graphics Forum, Vol. 39. Wiley Online Library, 91--105."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01531"},{"key":"e_1_3_2_1_22_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00053"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323042"},{"key":"e_1_3_2_1_26_1","first-page":"31841","article-title":"Get3d: A generative model of high quality 3d textured shapes learned from images","volume":"35","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. Advances In Neural Information Processing Systems, Vol. 35 (2022), 31841--31854.","journal-title":"Advances In Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","volume-title":"Stylenerf: A style-based 3d-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985","author":"Gu Jiatao","year":"2021","unstructured":"Jiatao Gu, Lingjie Liu, Peng Wang, and Christian Theobalt. 2021. Stylenerf: A style-based 3d-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_29_1","volume-title":"Openlrm: Open-source large reconstruction models.","author":"He Zexin","year":"2023","unstructured":"Zexin He and Tengfei Wang. 2023. Openlrm: Open-source large reconstruction models."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01008"},{"key":"e_1_3_2_1_31_1","volume-title":"Semantic anything in 3d gaussians. arXiv preprint arXiv:2401.17857","author":"Hu Xu","year":"2024","unstructured":"Xu Hu, Yuxi Wang, Lue Fan, Junsong Fan, Junran Peng, Zhen Lei, Qing Li, and Zhaoxiang Zhang. 2024. Semantic anything in 3d gaussians. arXiv preprint arXiv:2401.17857 (2024)."},{"key":"e_1_3_2_1_32_1","unstructured":"images.cv. 2024. CV image dataset. https:\/\/images.cv."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912445831"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00983"},{"key":"e_1_3_2_1_37_1","first-page":"1","article-title":"Modeling surface appearance from a single photograph using self-augmented convolutional neural networks","volume":"36","author":"Li Xiao","year":"2017","unstructured":"Xiao Li, Yue Dong, Pieter Peers, and Xin Tong. 2017. Modeling surface appearance from a single photograph using self-augmented convolutional neural networks. ACM Transactions on Graphics (ToG), Vol. 36, 4 (2017), 1--11.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_39_1","unstructured":"Minghua Liu Chao Xu Haian Jin Linghao Chen Zexiang Xu Hao Su et al. 2023. One-2--3--45: Any single image to 3d mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Citygaussian: Real-time high-quality large-scale scene rendering with gaussians. arXiv preprint arXiv:2404.01133","author":"Liu Yang","year":"2024","unstructured":"Yang Liu, He Guan, Chuanchen Luo, Lue Fan, Junran Peng, and Zhaoxiang Zhang. 2024. Citygaussian: Real-time high-quality large-scale scene rendering with gaussians. arXiv preprint arXiv:2404.01133 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation. arXiv preprint arXiv:2312.08754","author":"Liu Zexiang","year":"2023","unstructured":"Zexiang Liu, Yangguang Li, Youtian Lin, Xin Yu, Sida Peng, Yan-Pei Cao, Xiaojuan Qi, Xiaoshui Huang, Ding Liang, and Wanli Ouyang. 2023. UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation. arXiv preprint arXiv:2312.08754 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Xiaoxiao Long Yuan-Chen Guo Cheng Lin Yuan Liu Zhiyang Dou Lingjie Liu Yuexin Ma Song-Hai Zhang Marc Habermann Christian Theobalt et al. 2023. Wonder3d: Single image to 3d using cross-domain diffusion. arXiv preprint arXiv:2310.15008 (2023).","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_2_1_45_1","volume-title":"Material Palette: Extraction of Materials from a Single Image. arXiv preprint arXiv:2311.17060","author":"Lopes Ivan","year":"2023","unstructured":"Ivan Lopes, Fabio Pizzati, and Raoul de Charette. 2023. Material Palette: Extraction of Materials from a Single Image. arXiv preprint arXiv:2311.17060 (2023)."},{"key":"e_1_3_2_1_46_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018)."},{"key":"e_1_3_2_1_47_1","volume-title":"Inverse graphics gan: Learning to generate 3d shapes from unstructured 2d data. arXiv preprint arXiv:2002.12674","author":"Lunz Sebastian","year":"2020","unstructured":"Sebastian Lunz, Yingzhen Li, Andrew Fitzgibbon, and Nate Kushman. 2020. Inverse graphics gan: Learning to generate 3d shapes from unstructured 2d data. arXiv preprint arXiv:2002.12674 (2020)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14466"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13503--13513","author":"Or-El Roy","year":"2022","unstructured":"Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong Joon Park, and Ira Kemelmacher-Shlizerman. 2022. Stylesdf: High-resolution 3d-consistent image and geometry generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13503--13513."},{"key":"e_1_3_2_1_55_1","volume-title":"Photoshape: Photorealistic materials for large-scale shape collections. arXiv preprint arXiv:1809.09761","author":"Park Keunhong","year":"2018","unstructured":"Keunhong Park, Konstantinos Rematas, Ali Farhadi, and Steven M Seitz. 2018. Photoshape: Photorealistic materials for large-scale shape collections. arXiv preprint arXiv:1809.09761 (2018)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00973"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3276392"},{"key":"e_1_3_2_1_58_1","volume-title":"Efficient neural architecture transformation search in channel-level for object detection. Advances in neural information processing systems","author":"Peng Junran","year":"2019","unstructured":"Junran Peng, Ming Sun, ZHAO-XIANG ZHANG, Tieniu Tan, and Junjie Yan. 2019. Efficient neural architecture transformation search in channel-level for object detection. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_59_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_60_1","unstructured":"Guocheng Qian Jinjie Mai Abdullah Hamdi Jian Ren Aliaksandr Siarohin Bing Li Hsin-Ying Lee Ivan Skorokhodov Peter Wonka Sergey Tulyakov et al. 2023. Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors. arXiv preprint arXiv:2306.17843 (2023)."},{"key":"e_1_3_2_1_61_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618194"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"e_1_3_2_1_64_1","volume-title":"3d generation on imagenet. arXiv preprint arXiv:2303.01416","author":"Skorokhodov Ivan","year":"2023","unstructured":"Ivan Skorokhodov, Aliaksandr Siarohin, Yinghao Xu, Jian Ren, Hsin-Ying Lee, Peter Wonka, and Sergey Tulyakov. 2023. 3d generation on imagenet. arXiv preprint arXiv:2303.01416 (2023)."},{"key":"e_1_3_2_1_65_1","volume-title":"Conference on Robot Learning. PMLR, 87--96","author":"Smith Edward J","year":"2017","unstructured":"Edward J Smith and David Meger. 2017. Improved adversarial systems for 3d object generation and reconstruction. In Conference on Robot Learning. PMLR, 87--96."},{"key":"e_1_3_2_1_66_1","volume-title":"High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514","author":"Sun Ke","year":"2019","unstructured":"Ke Sun, Yang Zhao, Borui Jiang, Tianheng Cheng, Bin Xiao, Dong Liu, Yadong Mu, Xinggang Wang, Wenyu Liu, and Jingdong Wang. 2019. High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514 (2019)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00314"},{"key":"e_1_3_2_1_68_1","volume-title":"Triposr: Fast 3d object reconstruction from a single image. arXiv preprint arXiv:2403.02151","author":"Tochilkin Dmitry","year":"2024","unstructured":"Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, Adam Letts, Yangguang Li, Ding Liang, Christian Laforte, Varun Jampani, and Yan-Pei Cao. 2024. Triposr: Fast 3d object reconstruction from a single image. arXiv preprint arXiv:2403.02151 (2024)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_26"},{"key":"e_1_3_2_1_70_1","volume-title":"ControlMat: A Controlled Generative Approach to Material Capture. arXiv preprint arXiv:2309.01700","author":"Vecchio Giuseppe","year":"2023","unstructured":"Giuseppe Vecchio, Rosalie Martin, Arthur Roullier, Adrien Kaiser, Romain Rouffet, Valentin Deschaintre, and Tamy Boubekeur. 2023. ControlMat: A Controlled Generative Approach to Material Capture. arXiv preprint arXiv:2309.01700 (2023)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01260"},{"key":"e_1_3_2_1_72_1","volume-title":"Matfuse: Controllable material generation with diffusion models. arXiv preprint arXiv:2308.11408","author":"Vecchio Giuseppe","year":"2023","unstructured":"Giuseppe Vecchio, Renato Sortino, Simone Palazzo, and Concetto Spampinato. 2023. Matfuse: Controllable material generation with diffusion models. arXiv preprint arXiv:2308.11408 (2023)."},{"key":"e_1_3_2_1_73_1","volume-title":"Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. Advances in neural information processing systems","author":"Wu Jiajun","year":"2016","unstructured":"Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. 2016. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618168"},{"key":"e_1_3_2_1_76_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1912--1920","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1912--1920."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00900"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00428"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00464"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01801"},{"key":"e_1_3_2_1_83_1","volume-title":"DiffMat: Latent diffusion models for image-guided material generation. Visual Informatics","author":"Yuan Liang","year":"2024","unstructured":"Liang Yuan, Dingkun Yan, Suguru Saito, and Issei Fujishiro. 2024. DiffMat: Latent diffusion models for image-guided material generation. Visual Informatics (2024)."},{"key":"e_1_3_2_1_84_1","volume-title":"Furniscene: A large-scale 3d room dataset with intricate furnishing scenes. arXiv preprint arXiv:2401.03470","author":"Zhang Genghao","year":"2024","unstructured":"Genghao Zhang, Yuxi Wang, Chuanchen Luo, Shibiao Xu, Junran Peng, Zhaoxiang Zhang, and Man Zhang. 2024. Furniscene: A large-scale 3d room dataset with intricate furnishing scenes. arXiv preprint arXiv:2401.03470 (2024)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00595"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"e_1_3_2_1_87_1","volume-title":"Scenex: Procedural controllable large-scale scene generation via large-language models. arXiv preprint arXiv:2403.15698","author":"Zhou Mengqi","year":"2024","unstructured":"Mengqi Zhou, Jun Hou, Chuanchen Luo, Yuxi Wang, Zhaoxiang Zhang, and Junran Peng. 2024. Scenex: Procedural controllable large-scale scene generation via large-language models. arXiv preprint arXiv:2403.15698 (2024)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680757","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:42Z","timestamp":1750294662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680757"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":87,"alternative-id":["10.1145\/3664647.3680757","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680757","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}