{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:18:16Z","timestamp":1781335096348,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"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":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657403","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["MVD^2: Efficient Multiview 3D Reconstruction for Multiview Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2318-1863","authenticated-orcid":false,"given":"Xin-Yang","family":"Zheng","sequence":"first","affiliation":[{"name":"Tsinghua University, China and Microsoft Research Asia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3628-9777","authenticated-orcid":false,"given":"Hao","family":"Pan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7082-5664","authenticated-orcid":false,"given":"Yu-Xiao","family":"Guo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8788-2453","authenticated-orcid":false,"given":"Xin","family":"Tong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3768-6654","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Stability AI. 2023. Stable Zero123. https:\/\/huggingface.co\/stabilityai\/stable-zero123."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Rui Chen Yongwei Chen Ningxin Jiao and Kui Jia. 2023a. Fantasia3D: Disentangling geometry and appearance for high-quality text-to-3D content creation. In ICCV.","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Yang Chen Yingwei Pan Yehao Li Ting Yao and Tao Mei. 2023b. Control3D: Towards controllable text-to-3D generation. In ACM Multimedia. 1148\u20131156.","DOI":"10.1145\/3581783.3612489"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Zhiqin Chen and Hao Zhang. 2019. Learning implicit fields for generative shape modeling. In CVPR. 5939\u20135948.","DOI":"10.1109\/CVPR.2019.00609"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Yen-Chi Cheng Hsin-Ying Lee Sergey Tulyakov Alexander\u00a0G Schwing and Liang-Yan Gui. 2023. SDFusion: Multimodal 3D shape completion reconstruction and generation. In CVPR. 4456\u20134465.","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"e_1_3_2_2_6_1","volume-title":"Article 68","author":"da Silveira Thiago","year":"2022","unstructured":"Thiago L.\u00a0T. da Silveira, Paulo G.\u00a0L. Pinto, Jeffri Murrugarra-Llerena, and Cl\u00e1udio\u00a0R. Jung. 2022. 3D scene geometry estimation from 360\u00b0 imagery: A survey. ACM Comput. Surv. 55, 4, Article 68 (2022), 39\u00a0pages."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Matt Deitke Ruoshi Liu Matthew Wallingford Huong Ngo Oscar Michel Aditya Kusupati Alan Fan Christian Laforte Vikram Voleti Samir\u00a0Yitzhak Gadre 2023a. Objaverse-XL: A universe of 10M+ 3D objects. In NeurIPS.","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_2_2_8_1","volume-title":"Objaverse: A universe of annotated 3D objects. In CVPR. 13142\u201313153.","author":"Deitke Matt","year":"2023","unstructured":"Matt Deitke, Dustin Schwenk, Jordi Salvador, Luca Weihs, Oscar Michel, Eli VanderBilt, Ludwig Schmidt, Kiana Ehsani, Aniruddha Kembhavi, and Ali Farhadi. 2023b. Objaverse: A universe of annotated 3D objects. In CVPR. 13142\u201313153."},{"key":"e_1_3_2_2_9_1","volume-title":"Nerdi: Single-view nerf synthesis with language-guided diffusion as general image priors. In CVPR. 20637\u201320647.","author":"Deng Congyue","year":"2023","unstructured":"Congyue Deng, Chiyu Jiang, Charles\u00a0R Qi, Xinchen Yan, Yin Zhou, Leonidas Guibas, Dragomir Anguelov, 2023. Nerdi: Single-view nerf synthesis with language-guided diffusion as general image priors. In CVPR. 20637\u201320647."},{"key":"e_1_3_2_2_10_1","volume-title":"Google scanned objects: A high-quality dataset of 3D scanned household items","author":"Downs Laura","unstructured":"Laura Downs, Anthony Francis, Nate Koenig, Brandon Kinman, Ryan Hickman, Krista Reymann, Thomas\u00a0B McHugh, and Vincent Vanhoucke. 2022. Google scanned objects: A high-quality dataset of 3D scanned household items. In ICRA. IEEE, 2553\u20132560."},{"key":"e_1_3_2_2_11_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. In NeurIPS. 31841\u201331854."},{"key":"e_1_3_2_2_12_1","unstructured":"Anchit Gupta Wenhan Xiong Yixin Nie Ian Jones and Barlas O\u011fuz. 2023. 3DGen: Triplane latent diffusion for textured mesh generation. arXiv:2303.05371."},{"key":"e_1_3_2_2_13_1","unstructured":"Zexin He and Tengfei Wang. 2023. OpenLRM: Open-source large reconstruction models. https:\/\/github.com\/3DTopia\/OpenLRM."},{"key":"e_1_3_2_2_14_1","volume-title":"LRM: Large reconstruction model for single image to 3D. In ICLR.","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 ICLR."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Zixuan Huang Stefan Stojanov Anh Thai Varun Jampani and James\u00a0M Rehg. 2024. ZeroShape: Regression-based zero-shot shape reconstruction. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00959"},{"key":"e_1_3_2_2_16_1","volume-title":"Octree Transformer: Autoregressive 3D shape generation on hierarchically structured sequences. In CVPR. 2697\u20132706.","author":"Ibing Moritz","year":"2023","unstructured":"Moritz Ibing, Gregor Kobsik, and Leif Kobbelt. 2023. Octree Transformer: Autoregressive 3D shape generation on hierarchically structured sequences. In CVPR. 2697\u20132706."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Ajay Jain Ben Mildenhall Jonathan\u00a0T. Barron Pieter Abbeel and Ben Poole. 2022. Zero-shot text-guided object generation with dream fields. In CVPR. 867\u2013876.","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_2_18_1","unstructured":"Heewoo Jun and Alex Nichol. 2023. Shap-E: Generating conditional 3D implicit functions. arXiv:2305.02463."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_3_2_2_21_1","unstructured":"Jiahao Li Hao Tan Kai Zhang Zexiang Xu Fujun Luan Yinghao Xu Yicong Hong Kalyan Sunkavalli Greg Shakhnarovich and Sai Bi. 2024b. Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model. In ICLR."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Muheng Li Yueqi Duan Jie Zhou and Jiwen Lu. 2023. Diffusion-SDF: Text-to-shape via voxelized diffusion. In CVPR. 12642\u201312651.","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"e_1_3_2_2_23_1","unstructured":"Weiyu Li Rui Chen Xuelin Chen and Ping Tan. 2024a. SweetDreamer: Aligning geometric priors in 2D diffusion for consistent Text-to-3D. In ICLR."},{"key":"e_1_3_2_2_24_1","unstructured":"Minghua Liu Ruoxi Shi Linghao Chen Zhuoyang Zhang Chao Xu Xinyue Wei Hansheng Chen Chong Zeng Jiayuan Gu and Hao Su. 2024b. One-2-3-45++: Fast single image to 3D objects with consistent multi-view generation and 3D diffusion. In CVPR."},{"key":"e_1_3_2_2_25_1","unstructured":"Minghua Liu Chao Xu Haian Jin Linghao Chen Mukund\u00a0Varma T Zexiang Xu and Hao Su. 2023d. One-2-3-45: Any single image to 3D mesh in 45 seconds without per-shape optimization. In NeurIPS."},{"key":"e_1_3_2_2_26_1","unstructured":"Ruoshi Liu Rundi Wu Basile Van\u00a0Hoorick Pavel Tokmakov Sergey Zakharov and Carl Vondrick. 2023b. Zero-1-to-3: Zero-shot one image to 3D object. In ICCV."},{"key":"e_1_3_2_2_27_1","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 ICLR."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Yuxin Liu Minshan Xie Hanyuan Liu and Tien-Tsin Wong. 2023c. Text-guided texturing by synchronized multi-view diffusion. arXiv:2311.12891.","DOI":"10.1145\/3680528.3687621"},{"key":"e_1_3_2_2_29_1","volume-title":"ISS: Image as stepping stone for text-guided 3D shape generation. In ICLR.","author":"Liu Zhengzhe","year":"2023","unstructured":"Zhengzhe Liu, Peng Dai, Ruihui Li, Xiaojuan Qi, and Chi-Wing Fu. 2023a. ISS: Image as stepping stone for text-guided 3D shape generation. In ICLR."},{"key":"e_1_3_2_2_30_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 and Wenping Wang. 2024. Wonder3D: Single Image to 3D using Cross-Domain Diffusion. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Xiaoxiao Long Cheng Lin Peng Wang Taku Komura and Wenping Wang. 2022. SparseNeuS: Fast generalizable neural surface reconstruction from sparse views. In ECCV. 210\u2013227.","DOI":"10.1007\/978-3-031-19824-3_13"},{"key":"e_1_3_2_2_32_1","unstructured":"Yuanxun Lu Jingyang Zhang Shiwei Li Tian Fang David McKinnon Yanghai Tsin Long Quan Xun Cao and Yao Yao. 2024. Direct2.5: Diverse text-to-3D generation via multi-view 2.5D diffusion. In CVPR."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Luke Melas-Kyriazi Iro Laina Christian Rupprecht and Andrea Vedaldi. 2023. Realfusion: 360\u00b0 reconstruction of any object from a single image. In CVPR. 8446\u20138455.","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron and Ravi Ramamoorthi. 2020. NeRF: Representing scenes as neural radiance fields for view synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Paritosh Mittal Yen-Chi Cheng Maneesh Singh and Shubham Tulsiani. 2022. AutoSDF: Shape priors for 3D completion reconstruction and generation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"e_1_3_2_2_36_1","unstructured":"Charlie Nash Yaroslav Ganin SM\u00a0Ali Eslami and Peter Battaglia. 2020. PolyGen: An autoregressive generative model of 3D meshes. In ICML. 7220\u20137229."},{"key":"e_1_3_2_2_37_1","volume-title":"DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research","author":"Oquab Maxime","year":"2024","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy\u00a0V. Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel HAZIZA, Francisco Massa, Alaaeldin El-Nouby, Mido Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Herve Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_2_2_38_1","unstructured":"Yichen Ouyang Wenhao Chai Jiayi Ye Dapeng Tao Yibing Zhan and Gaoang Wang. 2023. Chasing consistency in text-to-3D generation from a single image. arXiv:2309.03599."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1017\/S096249291700006X"},{"key":"e_1_3_2_2_40_1","volume-title":"Dreamfusion: Text-to-3D using 2D diffusion. In ICLR.","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 ICLR."},{"key":"e_1_3_2_2_41_1","unstructured":"Senthil Purushwalkam and Nikhil Naik. 2023. ConRad: Image constrained radiance fields for 3D generation from a single image. In NeurIPS."},{"key":"e_1_3_2_2_42_1","unstructured":"Guocheng Qian Jinjie Mai Abdullah Hamdi Jian Ren Aliaksandr Siarohin Bing Li Hsin-Ying Lee Ivan Skorokhodov Peter Wonka Sergey Tulyakov 2024. Magic123: One image to high-quality 3D object generation using both 2D and 3D diffusion priors. In ICLR."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022a. High-resolution image synthesis with latent diffusion models. In CVPR. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_44_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. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Steven\u00a0M Seitz Brian Curless James Diebel Daniel Scharstein and Richard Szeliski. 2006. A comparison and evaluation of multi-view stereo reconstruction algorithms. In CVPR. 519\u2013528.","DOI":"10.1109\/CVPR.2006.19"},{"key":"e_1_3_2_2_46_1","unstructured":"Tianchang Shen Jun Gao Kangxue Yin Ming-Yu Liu and Sanja Fidler. 2021. Deep marching tetrahedra: A hybrid representation for high-resolution 3D shape synthesis. In NeurIPS. 6087\u20136101."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592430"},{"key":"e_1_3_2_2_48_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:2310.15110."},{"key":"e_1_3_2_2_49_1","unstructured":"Yichun Shi Peng Wang Jianglong Ye Mai Long Kejie Li and Xiao Yang. 2024. MVDream: Multi-view diffusion for 3D generation. In ICLR."},{"key":"e_1_3_2_2_50_1","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 ICLR."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Stanislaw Szymanowicz Christian Rupprecht and Andrea Vedaldi. 2024. Splatter image: Ultra-fast single-view 3D reconstruction. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"e_1_3_2_2_52_1","volume-title":"LGM: Large multi-view gaussian model for high-resolution 3D content creation. arXiv:2402.05054.","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Zhaoxi Chen, Xiaokang Chen, Tengfei Wang, Gang Zeng, and Ziwei Liu. 2024. LGM: Large multi-view gaussian model for high-resolution 3D content creation. arXiv:2402.05054."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Junshu Tang Tengfei Wang Bo Zhang Ting Zhang Ran Yi Lizhuang Ma and Dong Chen. 2023a. Make-It-3D: High-fidelity 3D creation from a single image with diffusion prior. In ICCV.","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"e_1_3_2_2_54_1","unstructured":"Shitao Tang Fuyang Zhang Jiacheng Chen Peng Wang and Yasutaka Furukawa. 2023b. MVDiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion. In NeurIPS."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"crossref","unstructured":"Haochen Wang Xiaodan Du Jiahao Li Raymond\u00a0A Yeh and Greg Shakhnarovich. 2023a. Score Jacobian chaining: Lifting pretrained 2D diffusion models for 3D generation. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"e_1_3_2_2_56_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. In NeurIPS."},{"key":"e_1_3_2_2_57_1","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 NeurIPS."},{"key":"e_1_3_2_2_58_1","unstructured":"Haohan Weng Tianyu Yang Jianan Wang Yu Li Tong Zhang CL Chen and Lei Zhang. 2023. Consistent123: Improve consistency for one image to 3D object synthesis. arXiv:2310.08092."},{"key":"e_1_3_2_2_59_1","unstructured":"Sangmin Woo Byeongjun Park Hyojun Go Jin-Young Kim and Changick Kim. 2024. HarmonyView: Harmonizing consistency and diversity in one-image-to-3D. In CVPR."},{"key":"e_1_3_2_2_60_1","unstructured":"Chao-Yuan Wu Justin Johnson Jitendra Malik Christoph Feichtenhofer and Georgia Gkioxari. 2023b. Multiview compressive coding for 3D reconstruction. In CVPR. 9065\u20139075."},{"key":"e_1_3_2_2_61_1","unstructured":"Haoyu Wu Alexandros Graikos and Dimitris Samaras. 2023a. S-VolSDF: Sparse multi-view stereo regularization of neural implicit surfaces. In ICCV. 3556\u20133568."},{"key":"e_1_3_2_2_62_1","volume-title":"AGG: Amortized generative 3D Gaussians for single image to 3D. arXiv:2401.04099.","author":"Xu Dejia","year":"2024","unstructured":"Dejia Xu, Ye Yuan, Morteza Mardani, Sifei Liu, Jiaming Song, Zhangyang Wang, and Arash Vahdat. 2024b. AGG: Amortized generative 3D Gaussians for single image to 3D. arXiv:2401.04099."},{"key":"e_1_3_2_2_63_1","volume-title":"GRM: Large Gaussian reconstruction model for efficient 3D reconstruction and generation. arXiv:2403.14621.","author":"Xu Yinghao","year":"2024","unstructured":"Yinghao Xu, Zifan Shi, Wang Yifan, Hansheng Chen, Ceyuan Yang, Sida Peng, Yujun Shen, and Gordon Wetzstein. 2024a. GRM: Large Gaussian reconstruction model for efficient 3D reconstruction and generation. arXiv:2403.14621."},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.090"},{"key":"e_1_3_2_2_65_1","unstructured":"Chen Yang Sikuang Li Jiemin Fang Ruofan Liang Lingxi Xie Xiaopeng Zhang Wei Shen and Qi Tian. 2024b. GaussianObject: Just taking four images to get a high-quality 3D object with Gaussian splatting. arXiv:2402.10259."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"crossref","unstructured":"Jiayu Yang Ziang Cheng Yunfei Duan Pan Ji and Hongdong Li. 2024a. ConsistNet: Enforcing 3D consistency for multi-view images diffusion. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00676"},{"key":"e_1_3_2_2_67_1","unstructured":"Jianglong Ye Peng Wang Kejie Li Yichun Shi and Heng Wang. 2023. Consistent-1-to-3: Consistent image to 3D view synthesis via geometry-aware diffusion models. In 3DV."},{"key":"e_1_3_2_2_68_1","unstructured":"Alex Yu Vickie Ye Matthew Tancik and Angjoo Kanazawa. 2021. pixelNeRF: Neural radiance fields from one or few images. In CVPR."},{"key":"e_1_3_2_2_69_1","unstructured":"Wangbo Yu Li Yuan Yan-Pei Cao Xiangjun Gao Xiaoyu Li Long Quan Ying Shan and Yonghong Tian. 2023. HiFi-123: Towards high-fidelity one image to 3D content generation. arXiv:2310.06744."},{"key":"e_1_3_2_2_70_1","unstructured":"Bohan Zeng Shanglin Li Yutang Feng Hong Li Sicheng Gao Jiaming Liu Huaxia Li Xu Tang Jianzhuang Liu and Baochang Zhang. 2023. IPDreamer: Appearance-controllable 3D object generation with image prompts. arXiv:2310.05375."},{"key":"e_1_3_2_2_71_1","unstructured":"Biao Zhang Matthias Nie\u00dfner and Peter Wonka. 2022. 3DILG: Irregular latent grids for 3D generative modeling. In NeurIPS."},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei\u00a0A Efros Eli Shechtman and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14602"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592103"},{"key":"e_1_3_2_2_76_1","unstructured":"Zi-Xin Zou Zhipeng Yu Yuan-Chen Guo Yangguang Li Ding Liang Yan-Pei Cao and Song-Hai Zhang. 2024. Triplane meets Gaussian splatting: Fast and generalizable single-view 3D reconstruction with transformers. In CVPR."}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657403","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:35Z","timestamp":1750295375000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":76,"alternative-id":["10.1145\/3641519.3657403","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657403","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}