{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T16:10:49Z","timestamp":1733933449146,"version":"3.30.2"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,10]]},"DOI":"10.1145\/3610548.3618168","type":"proceedings-article","created":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T17:28:40Z","timestamp":1702315720000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5557-0623","authenticated-orcid":false,"given":"Tong","family":"Wu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong and Shanghai AI Laboratory, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4528-5495","authenticated-orcid":false,"given":"Zhibing","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong and Shanghai AI Laboratory, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9552-4320","authenticated-orcid":false,"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China and Shanghai AI Laboratory, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7195-4159","authenticated-orcid":false,"given":"Pan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5825-9467","authenticated-orcid":false,"given":"Xingang","family":"Pan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6877-5353","authenticated-orcid":false,"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8865-7896","authenticated-orcid":false,"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong and Shanghai AI Laboratory, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2023,12,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0902-9"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"volume-title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation. arXiv preprint arXiv:2303.13873","year":"2023","author":"Chen Rui","key":"e_1_3_2_2_3_1","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)."},{"volume-title":"TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition. In Advances in Neural Information Processing Systems (NeurIPS).","year":"2022","author":"Chen Yongwei","key":"e_1_3_2_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. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01015"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"volume-title":"International Conference on Machine Learning.","year":"2023","author":"Gu Jiatao","key":"e_1_3_2_2_8_1","unstructured":"Jiatao Gu, Alex Trevithick, Kai-En Lin, Josh Susskind, Christian Theobalt, Lingjie Liu, and Ravi Ramamoorthi. 2023. NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_9_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. (2022).","DOI":"10.1109\/CVPR52688.2022.00094"},{"volume-title":"Kaolin: A pytorch library for accelerating 3d deep learning research. arXiv preprint arXiv:1911.05063","year":"2019","author":"Jatavallabhula Krishna\u00a0Murthy","key":"e_1_3_2_2_10_1","unstructured":"Krishna\u00a0Murthy Jatavallabhula, Edward Smith, Jean-Francois Lafleche, Clement\u00a0Fuji Tsang, Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian, and Sanja Fidler. 2019. Kaolin: A pytorch library for accelerating 3d deep learning research. arXiv preprint arXiv:1911.05063 (2019)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"volume-title":"Shap-E: Generating Conditional 3D Implicit Functions. arXiv preprint arXiv:2305.02463","year":"2023","author":"Jun Heewoo","key":"e_1_3_2_2_12_1","unstructured":"Heewoo Jun and Alex Nichol. 2023. Shap-E: Generating Conditional 3D Implicit Functions. arXiv preprint arXiv:2305.02463 (2023)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"volume-title":"arXiv:2304.02643","year":"2023","author":"Kirillov Alexander","key":"e_1_3_2_2_14_1","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander\u00a0C. Berg, Wan-Yen Lo, Piotr Doll\u00e1r, and Ross Girshick. 2023. Segment Anything. arXiv:2304.02643 (2023)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_2_16_1","unstructured":"Ruoshi Liu Rundi Wu Basile\u00a0Van Hoorick Pavel Tokmakov Sergey Zakharov and Carl Vondrick. 2023. Zero-1-to-3: Zero-shot One Image to 3D Object. arxiv:2303.11328\u00a0[cs.CV]"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_47"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00692-1_1"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Luke Melas-Kyriazi Christian Rupprecht Iro Laina and Andrea Vedaldi. 2023b. RealFusion: 360 Reconstruction of Any Object from a Single Image. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Luke Melas-Kyriazi Christian Rupprecht and Andrea Vedaldi. 2023a. PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction. In Arxiv.","DOI":"10.1109\/CVPR52729.2023.01242"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P. Srinivasan Matthew Tancik Jonathan\u00a0T. Barron Ravi Ramamoorthi and Ren Ng. 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_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00810"},{"volume-title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts. arXiv preprint arXiv:2212.08751","year":"2022","author":"Nichol Alex","key":"e_1_3_2_2_25_1","unstructured":"Alex Nichol, Heewoo Jun, Prafulla Dhariwal, Pamela Mishkin, and Mark Chen. 2022. Point-E: A System for Generating 3D Point Clouds from Complex Prompts. arXiv preprint arXiv:2212.08751 (2022)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00427"},{"volume-title":"DreamFusion: Text-to-3D using 2D Diffusion. arXiv","year":"2022","author":"Poole Ben","key":"e_1_3_2_2_27_1","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. arXiv (2022)."},{"volume-title":"International conference on machine learning. PMLR, 8748\u20138763","year":"2021","author":"Radford Alec","key":"e_1_3_2_2_28_1","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"volume-title":"Vision Transformers for Dense Prediction. ICCV","year":"2021","author":"Ranftl Ren\u00e9","key":"e_1_3_2_2_29_1","unstructured":"Ren\u00e9 Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. 2021. Vision Transformers for Dense Prediction. ICCV (2021)."},{"volume-title":"Texture: Text-guided texturing of 3d shapes. arXiv preprint arXiv:2302.01721","year":"2023","author":"Richardson Elad","key":"e_1_3_2_2_30_1","unstructured":"Elad Richardson, Gal Metzer, Yuval Alaluf, Raja Giryes, and Daniel Cohen-Or. 2023. Texture: Text-guided texturing of 3d shapes. arXiv preprint arXiv:2302.01721 (2023)."},{"key":"e_1_3_2_2_31_1","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv:2112.10752\u00a0[cs.CV]"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Shen Sang and M. Chandraker. 2020. Single-Shot Neural Relighting and SVBRDF Estimation. In ECCV.","DOI":"10.1007\/978-3-030-58529-7_6"},{"key":"e_1_3_2_2_33_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 Advances in Neural Information Processing Systems (NeurIPS)."},{"volume-title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior. arXiv preprint arXiv:2303.14184","year":"2023","author":"Tang Junshu","key":"e_1_3_2_2_34_1","unstructured":"Junshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, and Dong Chen. 2023. Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior. arXiv preprint arXiv:2303.14184 (2023)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.30"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Kalyan\u00a0Alwala Vasudev Abhinav Gupta and Shubham Tulsiani. 2022. Pre-train Self-train Distill: A simple recipe for Supersizing 3D Reconstruction. In Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.00375"},{"volume-title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation. arXiv preprint arXiv:2212.00774","year":"2022","author":"Wang Haochen","key":"e_1_3_2_2_37_1","unstructured":"Haochen Wang, Xiaodan Du, Jiahao Li, Raymond\u00a0A. Yeh, and Greg Shakhnarovich. 2022. Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation. arXiv preprint arXiv:2212.00774 (2022)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01794"},{"volume-title":"Multiview Compressive Coding for 3D Reconstruction. arXiv preprint arXiv:2301.08247","year":"2023","author":"Wu Chao-Yuan","key":"e_1_3_2_2_39_1","unstructured":"Chao-Yuan Wu, Justin Johnson, Jitendra Malik, Christoph Feichtenhofer, and Georgia Gkioxari. 2023. Multiview Compressive Coding for 3D Reconstruction. arXiv preprint arXiv:2301.08247 (2023)."},{"key":"e_1_3_2_2_40_1","unstructured":"Dejia Xu Yifan Jiang Peihao Wang Zhiwen Fan Yi Wang and Zhangyang Wang. 2022. NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360\u00b0 Views. arXiv preprint arXiv:2211.16431."},{"volume-title":"Computer Graphics Forum, Vol.\u00a031","author":"Yan Ling-Qi","key":"e_1_3_2_2_41_1","unstructured":"Ling-Qi Yan, Yahan Zhou, Kun Xu, and Rui Wang. 2012. Accurate translucent material rendering under spherical Gaussian lights. In Computer Graphics Forum, Vol.\u00a031. Wiley Online Library, 2267\u20132276."},{"volume-title":"PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","year":"2021","author":"Zhang Kai","key":"e_1_3_2_2_42_1","unstructured":"Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, and Noah Snavely. 2021. PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"volume-title":"Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543","year":"2023","author":"Zhang Lvmin","key":"e_1_3_2_2_43_1","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)."}],"event":{"name":"SA '23: SIGGRAPH Asia 2023","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Sydney NSW Australia","acronym":"SA '23"},"container-title":["SIGGRAPH Asia 2023 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610548.3618168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T12:02:24Z","timestamp":1733832144000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610548.3618168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,10]]},"references-count":43,"alternative-id":["10.1145\/3610548.3618168","10.1145\/3610548"],"URL":"https:\/\/doi.org\/10.1145\/3610548.3618168","relation":{},"subject":[],"published":{"date-parts":[[2023,12,10]]},"assertion":[{"value":"2023-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}