{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:00Z","timestamp":1784268600153,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":64,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2024QY1400"],"award-info":[{"award-number":["2024QY1400"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681276","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"6880-6889","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["PlacidDreamer: Advancing Harmony in Text-to-3D Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7100-1067","authenticated-orcid":false,"given":"Shuo","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2370-8841","authenticated-orcid":false,"given":"Shikun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7291-6198","authenticated-orcid":false,"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9720-3220","authenticated-orcid":false,"given":"Xiaoyu","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7271-2858","authenticated-orcid":false,"given":"Yanmin","family":"Xiong","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4839-9520","authenticated-orcid":false,"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-565X","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5475-2728","authenticated-orcid":false,"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8449-278X","authenticated-orcid":false,"given":"Jia","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, Tsinghua University & Key Laboratory of Pervasive Computing, Ministry of Education, 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","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models. arXiv preprint arXiv:2304.00916","author":"Cao Yukang","year":"2023","unstructured":"Yukang Cao, Yan-Pei Cao, Kai Han, Ying Shan, and Kwan-Yee K Wong. 2023. Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models. arXiv preprint arXiv:2304.00916 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_1_4_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_5_1","volume-title":"It3d: Improved text-to-3d generation with explicit view synthesis. arXiv preprint arXiv:2308.11473","author":"Chen Yiwen","year":"2023","unstructured":"Yiwen Chen, Chi Zhang, Xiaofeng Yang, Zhongang Cai, Gang Yu, Lei Yang, and Guosheng Lin. 2023. It3d: Improved text-to-3d generation with explicit view synthesis. arXiv preprint arXiv:2308.11473 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Text-to-3d using gaussian splatting. arXiv preprint arXiv:2309.16585","author":"Chen Zilong","year":"2023","unstructured":"Zilong Chen, Feng Wang, and Huaping Liu. 2023. Text-to-3d using gaussian splatting. arXiv preprint arXiv:2309.16585 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems.","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. In Proceedings of Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_10_1","unstructured":"Yuze He Yushi Bai Matthieu Lin Wang Zhao Yubin Hu Jenny Sheng Ran Yi Juanzi Li and Yong-Jin Liu. 2023. T^3Bench: Benchmarking Current Progress in Text-to-3D Generation. arxiv: 2310.02977 [cs.CV]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems.","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Proceedings of Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_13_1","volume-title":"Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400","author":"Hong Yicong","year":"2023","unstructured":"Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2023. Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:2311.04400 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612022"},{"key":"e_1_3_2_1_16_1","volume-title":"DreamTime: An Improved Optimization Strategy for Text-to-3D Content Creation. arXiv preprint arXiv:2306.12422","author":"Huang Yukun","year":"2023","unstructured":"Yukun Huang, Jianan Wang, Yukai Shi, Xianbiao Qi, Zheng-Jun Zha, and Lei Zhang. 2023. DreamTime: An Improved Optimization Strategy for Text-to-3D Content Creation. arXiv preprint arXiv:2306.12422 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"DreamWaltz: Make a Scene with Complex 3D Animatable Avatars. arXiv preprint arXiv:2305.12529","author":"Huang Yukun","year":"2023","unstructured":"Yukun Huang, Jianan Wang, Ailing Zeng, He Cao, Xianbiao Qi, Yukai Shi, Zheng-Jun Zha, and Lei Zhang. 2023. DreamWaltz: Make a Scene with Complex 3D Animatable Avatars. arXiv preprint arXiv:2305.12529 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_1_19_1","volume-title":"AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control. arXiv preprint arXiv:2303.17606","author":"Jiang Ruixiang","year":"2023","unstructured":"Ruixiang Jiang, Can Wang, Jingbo Zhang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. 2023. AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control. arXiv preprint arXiv:2303.17606 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Shap-e: Generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463","author":"Jun Heewoo","year":"2023","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_1_21_1","volume-title":"Noise-free score distillation. arXiv preprint arXiv:2310.17590","author":"Katzir Oren","year":"2023","unstructured":"Oren Katzir, Or Patashnik, Daniel Cohen-Or, and Dani Lischinski. 2023. Noise-free score distillation. arXiv preprint arXiv:2310.17590 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_23_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Sweetdreamer: Aligning geometric priors in 2d diffusion for consistent text-to-3d. arXiv preprint arXiv:2310.02596","author":"Li Weiyu","year":"2023","unstructured":"Weiyu Li, Rui Chen, Xuelin Chen, and Ping Tan. 2023. Sweetdreamer: Aligning geometric priors in 2d diffusion for consistent text-to-3d. arXiv preprint arXiv:2310.02596 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Yixun Liang Xin Yang Jiantao Lin Haodong Li Xiaogang Xu and Yingcong Chen. 2023. LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching. arxiv: 2311.11284 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_27_1","volume-title":"Consistent123: One image to highly consistent 3d asset using case-aware diffusion priors. arXiv preprint arXiv:2309.17261","author":"Lin Yukang","year":"2023","unstructured":"Yukang Lin, Haonan Han, Chaoqun Gong, Zunnan Xu, Yachao Zhang, and Xiu Li. 2023. Consistent123: One image to highly consistent 3d asset using case-aware diffusion priors. arXiv preprint arXiv:2309.17261 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"One-2--3--45: Fast single image to 3d objects with consistent multi-view generation and 3d diffusion. arXiv preprint arXiv:2311.07885","author":"Liu Minghua","year":"2023","unstructured":"Minghua Liu, Ruoxi Shi, Linghao Chen, Zhuoyang Zhang, Chao Xu, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, and Hao Su. 2023. One-2--3--45: Fast single image to 3d objects with consistent multi-view generation and 3d diffusion. arXiv preprint arXiv:2311.07885 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_2_1_30_1","volume-title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image. arXiv preprint arXiv:2309.03453","author":"Liu Yuan","year":"2023","unstructured":"Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, and Wenping Wang. 2023. SyncDreamer: Generating Multiview-consistent Images from a Single-view Image. arXiv preprint arXiv:2309.03453 (2023)."},{"key":"e_1_3_2_1_31_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_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"e_1_3_2_1_33_1","unstructured":"Baorui Ma Haoge Deng Junsheng Zhou Yu-Shen Liu Tiejun Huang and Xinlong Wang. 2023. GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation. arXiv preprint arXiv:2311.17971."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_36_1","volume-title":"Point-e: A system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751","author":"Nichol Alex","year":"2022","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_1_37_1","volume-title":"International Conference on Machine Learning. PMLR, 8162--8171","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning. PMLR, 8162--8171."},{"key":"e_1_3_2_1_38_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_39_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_40_1","volume-title":"Mutian Xu, Yushuang Wu, Weihao Yuan, Zilong Dong, Liefeng Bo, and Xiaoguang Han.","author":"Qiu Lingteng","year":"2023","unstructured":"Lingteng Qiu, Guanying Chen, Xiaodong Gu, Qi zuo, Mutian Xu, Yushuang Wu, Weihao Yuan, Zilong Dong, Liefeng Bo, and Xiaoguang Han. 2023. RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. arXiv preprint arXiv:2311.16918 (2023)."},{"key":"e_1_3_2_1_41_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_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_43_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_44_1","volume-title":"Dmitry Lagun, Li Fei-Fei, Deqing Sun, et al.","author":"Sargent Kyle","year":"2023","unstructured":"Kyle Sargent, Zizhang Li, Tanmay Shah, Charles Herrmann, Hong-Xing Yu, Yunzhi Zhang, Eric Ryan Chan, Dmitry Lagun, Li Fei-Fei, Deqing Sun, et al. 2023. Zeronvs: Zero-shot 360-degree view synthesis from a single real image. arXiv preprint arXiv:2310.17994 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512","author":"Shi Yichun","year":"2023","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, and Xiao Yang. 2023. Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of International Conference on Machine Learning.","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In Proceedings of International Conference on Machine Learning."},{"key":"e_1_3_2_1_47_1","volume-title":"Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_48_1","volume-title":"Dreamcraft3d: Hierarchical 3d generation with bootstrapped diffusion prior. arXiv preprint arXiv:2310.16818","author":"Sun Jingxiang","year":"2023","unstructured":"Jingxiang Sun, Bo Zhang, Ruizhi Shao, Lizhen Wang, Wen Liu, Zhenda Xie, and Yebin Liu. 2023. Dreamcraft3d: Hierarchical 3d generation with bootstrapped diffusion prior. arXiv preprint arXiv:2310.16818 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. PMLR, 33115--33134","author":"Sun Shikun","year":"2023","unstructured":"Shikun Sun, Longhui Wei, Junliang Xing, Jia Jia, and Qi Tian. 2023. SDDM: score-decomposed diffusion models on manifolds for unpaired image-to-image translation. In International Conference on Machine Learning. PMLR, 33115--33134."},{"key":"e_1_3_2_1_50_1","volume-title":"Stable Score Distillation for High-Quality 3D Generation. arXiv preprint arXiv:2312.09305","author":"Tang Boshi","year":"2023","unstructured":"Boshi Tang, Jianan Wang, Zhiyong Wu, and Lei Zhang. 2023. Stable Score Distillation for High-Quality 3D Generation. arXiv preprint arXiv:2312.09305 (2023)."},{"key":"e_1_3_2_1_51_1","volume-title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation. arXiv preprint 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 preprint arXiv:2402.05054 (2024)."},{"key":"e_1_3_2_1_52_1","volume-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653","author":"Tang Jiaxiang","year":"2023","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:2309.16653 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"e_1_3_2_1_54_1","unstructured":"Peihao Wang Zhiwen Fan Dejia Xu Dilin Wang Sreyas Mohan Forrest Iandola Rakesh Ranjan Yilei Li Qiang Liu Zhangyang Wang et al. 2023. SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity. arXiv preprint arXiv:2401.00604 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. arXiv preprint arXiv:2305.16213","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. arXiv preprint arXiv:2305.16213 (2023)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00317"},{"key":"e_1_3_2_1_57_1","volume-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977 (2023)."},{"key":"e_1_3_2_1_58_1","volume-title":"SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance. arXiv preprint arXiv:2312.08889","author":"Xu Yuanyou","year":"2023","unstructured":"Yuanyou Xu, Zongxin Yang, and Yi Yang. 2023. SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance. arXiv preprint arXiv:2312.08889 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Consistnet: Enforcing 3d consistency for multi-view images diffusion. arXiv preprint arXiv:2310.10343","author":"Yang Jiayu","year":"2023","unstructured":"Jiayu Yang, Ziang Cheng, Yunfei Duan, Pan Ji, and Hongdong Li. 2023. Consistnet: Enforcing 3d consistency for multi-view images diffusion. arXiv preprint arXiv:2310.10343 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors. arXiv preprint arXiv:2310.08529","author":"Yi Taoran","year":"2023","unstructured":"Taoran Yi, Jiemin Fang, Guanjun Wu, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Qi Tian, and Xinggang Wang. 2023. Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors. arXiv preprint arXiv:2310.08529 (2023)."},{"key":"e_1_3_2_1_61_1","volume-title":"Text-to-3d with classifier score distillation. arXiv preprint arXiv:2310.19415","author":"Yu Xin","year":"2023","unstructured":"Xin Yu, Yuan-Chen Guo, Yangguang Li, Ding Liang, Song-Hai Zhang, and Xiaojuan Qi. 2023. Text-to-3d with classifier score distillation. arXiv preprint arXiv:2310.19415 (2023)."},{"key":"e_1_3_2_1_62_1","volume-title":"AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation. arXiv preprint arXiv:2306.09864","author":"Zeng Yifei","year":"2023","unstructured":"Yifei Zeng, Yuanxun Lu, Xinya Ji, Yao Yao, Hao Zhu, and Xun Cao. 2023. AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation. arXiv preprint arXiv:2306.09864 (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Prior. arXiv preprint arXiv:2308.13223","author":"Zhao Minda","year":"2023","unstructured":"Minda Zhao, Chaoyi Zhao, Xinyue Liang, Lincheng Li, Zeng Zhao, Zhipeng Hu, Changjie Fan, and Xin Yu. 2023. EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Prior. arXiv preprint arXiv:2308.13223 (2023)."},{"key":"e_1_3_2_1_64_1","volume-title":"HiFA: High-fidelity Text-to-3D with Advanced Diffusion Guidance. arXiv preprint arXiv:2305.18766","author":"Zhu Joseph","year":"2023","unstructured":"Joseph Zhu and Peiye Zhuang. 2023. HiFA: High-fidelity Text-to-3D with Advanced Diffusion Guidance. arXiv preprint arXiv:2305.18766 (2023)."}],"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\/3664647.3681276","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:43Z","timestamp":1750295863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":64,"alternative-id":["10.1145\/3664647.3681276","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681276","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"}}]}}