{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:19:03Z","timestamp":1783095543055,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":64,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687676","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":6,"title":["Boosting 3D object generation through PBR materials"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1373-4427","authenticated-orcid":false,"given":"Yitong","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8858-0918","authenticated-orcid":false,"given":"Xudong","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6992-0089","authenticated-orcid":false,"given":"Li","family":"Ma","sequence":"additional","affiliation":[{"name":"Scanline VFX Studio, Los Angeles, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5823-2722","authenticated-orcid":false,"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0777-9232","authenticated-orcid":false,"given":"Bo","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_3_2_4_1","unstructured":"Yongwei Chen Rui Chen Jiabao Lei Yabin Zhang and Kui Jia. 2022. Tango: Text-driven photorealistic and robust 3d stylization via lighting decomposition. (2022)."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27886"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"e_1_3_3_2_7_1","series-title":"(NIPS \u201923)","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Deitke Matt","year":"2024","unstructured":"Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir\u00a0Yitzhak Gadre, Eli VanderBilt, Aniruddha Kembhavi, Carl Vondrick, Georgia Gkioxari, Kiana Ehsani, Ludwig Schmidt, and Ali Farhadi. 2024. Objaverse-XL: a universe of 10M+ 3D objects. In Proceedings of the 37th International Conference on Neural Information Processing Systems(NIPS \u201923). Curran Associates Inc., Red Hook, NY, USA, Article 1554, 15\u00a0pages."},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Valentin Deschaintre Miika Aittala Fredo Durand George Drettakis and Adrien Bousseau. 2018. Single-image svbrdf capture with a rendering-aware deep network. ACM Transactions on Graphics 37 4 (2018) 1\u201315.","DOI":"10.1145\/3197517.3201378"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"crossref","unstructured":"David Forsyth and Jason\u00a0J Rock. 2021. Intrinsic image decomposition using paradigms. IEEE transactions on pattern analysis and machine intelligence 44 11 (2021) 7624\u20137637.","DOI":"10.1109\/TPAMI.2021.3119551"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Duan Gao Xiao Li Yue Dong Pieter Peers Kun Xu and Xin Tong. 2019. Deep inverse rendering for high-resolution SVBRDF estimation from an arbitrary number of images. ACM Transactions on Graphics 38 4 (2019) 134\u20131.","DOI":"10.1145\/3306346.3323042"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Yu Guo Cameron Smith Milo\u0161 Ha\u0161an Kalyan Sunkavalli and Shuang Zhao. 2020. MaterialGAN: reflectance capture using a generative SVBRDF model. ACM Transactions on Graphics (TOG) 39 6 (2020) 1\u201313.","DOI":"10.1145\/3414685.3417779"},{"key":"e_1_3_3_2_13_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_14_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hong Yicong","year":"2024","unstructured":"Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2024. LRM: Large Reconstruction Model for Single Image to 3D. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sllU8vvsFF"},{"key":"e_1_3_3_2_15_1","first-page":"8153","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu Li","year":"2024","unstructured":"Li Hu, Xin Gao, Peng Zhang, Ke Sun, Bang Zhang, and Liefeng Bo. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8153\u20138163."},{"key":"e_1_3_3_2_16_1","unstructured":"Yi Huang Jiancheng Huang Yifan Liu Mingfu Yan Jiaxi Lv Jianzhuang Liu Wei Xiong He Zhang Shifeng Chen and Liangliang Cao. 2024. Diffusion Model-Based Image Editing: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2402.17525\u00a0[cs.CV]"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.573"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Kaizhang Kang Zimin Chen Jiaping Wang Kun Zhou and Hongzhi Wu. 2018. Efficient reflectance capture using an autoencoder. ACM Transactions on Graphics (TOG) 37 4 (2018) 1\u201310.","DOI":"10.1145\/3197517.3201279"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00894"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Peter Kocsis Vincent Sitzmann and Matthias Nie\u00dfner. 2024b. Intrinsic Image Diffusion for Indoor Single-view Material Estimation. Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR52733.2024.00497"},{"key":"e_1_3_3_2_23_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li Jiahao","year":"2024","unstructured":"Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, and Sai Bi. 2024c. Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2lDQLiH1W4"},{"key":"e_1_3_3_2_24_1","unstructured":"Peng Li Yuan Liu Xiaoxiao Long Feihu Zhang Cheng Lin Mengfei Li Xingqun Qi Shanghang Zhang Wenhan Luo Ping Tan et\u00a0al. 2024b. Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.11616 (2024)."},{"key":"e_1_3_3_2_25_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li Weiyu","year":"2024","unstructured":"Weiyu Li, Rui Chen, Xuelin Chen, and Ping Tan. 2024a. SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=extpNXo6hB"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680994"},{"key":"e_1_3_3_2_28_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong\u00a0Jae Lee. 2023c. Visual Instruction Tuning. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=w0H2xGHlkw"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_3_2_31_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu Yuan","year":"2024","unstructured":"Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, and Wenping Wang. 2024a. SyncDreamer: Generating Multiview-consistent Images from a Single-view Image. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=MN3yH2ovHb"},{"key":"e_1_3_3_2_32_1","volume-title":"International Conference on Learning Representations","author":"Liu Zhen","year":"2023","unstructured":"Zhen Liu, Yao Feng, Michael\u00a0J. Black, Derek Nowrouzezahrai, Liam Paull, and Weiyang Liu. 2023a. MeshDiffusion: Score-based Generative 3D Mesh Modeling. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=0cpM2ApF9p6"},{"key":"e_1_3_3_2_33_1","unstructured":"Zexiang Liu Yangguang Li Youtian Lin Xin Yu Sida Peng Yan-Pei Cao Xiaojuan Qi Xiaoshui Huang Ding Liang and Wanli Ouyang. 2023b. UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.08754 (2023)."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00419"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01242"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"e_1_3_3_2_38_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2023. Dreamfusion: Text-to-3d using 2d diffusion. (2023)."},{"key":"e_1_3_3_2_39_1","volume-title":"The Twelfth International Conference on Learning Representations (ICLR)","author":"Qian Guocheng","year":"2024","unstructured":"Guocheng Qian, Jinjie Mai, Abdullah Hamdi, Jian Ren, Aliaksandr Siarohin, Bing Li, Hsin-Ying Lee, Ivan Skorokhodov, Peter Wonka, Sergey Tulyakov, and Bernard Ghanem. 2024. Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. In The Twelfth International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=0jHkUDyEO9"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"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","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022b. High-resolution image synthesis with latent diffusion models. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_6"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618194"},{"key":"e_1_3_3_2_47_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shi Yichun","year":"2024","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FUgrjq2pbB"},{"key":"e_1_3_3_2_48_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sun Jingxiang","year":"2024","unstructured":"Jingxiang Sun, Bo Zhang, Ruizhi Shao, Lizhen Wang, Wen Liu, Zhenda Xie, and Yebin Liu. 2024. DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=DDX1u29Gqr"},{"key":"e_1_3_3_2_49_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2024. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=UyNXMqnN3c"},{"key":"e_1_3_3_2_50_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew\u00a0M Dai Anja Hauth et\u00a0al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11805 (2023)."},{"key":"e_1_3_3_2_51_1","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:https:\/\/arXiv.org\/abs\/2403.02151 (2024)."},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"crossref","unstructured":"Shimon Vainer Mark Boss Mathias Parger Konstantin Kutsy Dante De\u00a0Nigris Ciara Rowles Nicolas Perony and Simon Donn\u00e9. 2024. Collaborative Control for Geometry-Conditioned PBR Image Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.05919 (2024).","DOI":"10.1007\/978-3-031-72624-8_8"},{"key":"e_1_3_3_2_53_1","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:https:\/\/arXiv.org\/abs\/2309.01700 (2023)."},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"e_1_3_3_2_55_1","unstructured":"Peng Wang Lingjie Liu Yuan Liu Christian Theobalt Taku Komura and Wenping Wang. 2021. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. (2021)."},{"key":"e_1_3_3_2_56_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Hao Tan, Sai Bi, Yinghao Xu, Fujun Luan, Kalyan Sunkavalli, Wenping Wang, Zexiang Xu, and Kai Zhang. 2024a. PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=noe76eRcPC"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"e_1_3_3_2_58_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023b. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_59_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Wang Zhengyi","year":"2024","unstructured":"Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, and Jun Zhu. 2024b. CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01794"},{"key":"e_1_3_3_2_61_1","unstructured":"Jiale Xu Weihao Cheng Yiming Gao Xintao Wang Shenghua Gao and Ying Shan. 2024a. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.07191 (2024)."},{"key":"e_1_3_3_2_62_1","unstructured":"Xudong Xu Zhaoyang Lyu Xingang Pan and Bo Dai. 2023. Matlaber: Material-aware text-to-3d via latent brdf auto-encoder. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.09278 (2023)."},{"key":"e_1_3_3_2_63_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu Yinghao","year":"2024","unstructured":"Yinghao Xu, Hao Tan, Fujun Luan, Sai Bi, Peng Wang, Jiahao Li, Zifan Shi, Kalyan Sunkavalli, Gordon Wetzstein, Zexiang Xu, and Kai Zhang. 2024b. DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=H4yQefeXhp"},{"key":"e_1_3_3_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00416"},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657445"}],"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\/3680528.3687676","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687676","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\/3680528.3687676"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":64,"alternative-id":["10.1145\/3680528.3687676","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687676","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"}}]}}