{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:23:49Z","timestamp":1787509429820,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","funder":[{"name":"The Major Key Project of PCL","award":["PCL2024A02"],"award-info":[{"award-number":["PCL2024A02"]}]},{"name":"Natural Science Foundation of China","award":["62271013,62031013"],"award-info":[{"award-number":["62271013,62031013"]}]},{"name":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology","award":["2024B1212010006"],"award-info":[{"award-number":["2024B1212010006"]}]},{"name":"Guangdong Province Pearl River Talent Program","award":["2021QN020708"],"award-info":[{"award-number":["2021QN020708"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024A1515010155"],"award-info":[{"award-number":["2024A1515010155"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20240813160202004, JCYJ20230807120808017"],"award-info":[{"award-number":["JCYJ20240813160202004, JCYJ20230807120808017"]}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","award":["GXWD20201231165807007-20200806163656003"],"award-info":[{"award-number":["GXWD20201231165807007-20200806163656003"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758302","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"13398-13404","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["T23D-QA: An Open Dataset and Benchmark for Text-driven 3D Generation Quality Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1481-8325","authenticated-orcid":false,"given":"Haohui","family":"Li","sequence":"first","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8960-5476","authenticated-orcid":false,"given":"Bowen","family":"Qu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7429-5495","authenticated-orcid":false,"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"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":"Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012","author":"Chang Angel X","year":"2015","unstructured":"015)]% chang2015shapenet , Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al., 2015. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_2_1_4_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, G Heigold, S Gelly, et al., 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_6_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_7_1","unstructured":"Yuan-Chen Guo Ying-Tian Liu Ruizhi Shao Christian Laforte Vikram Voleti Guan Luo Chia-Hao Chen Zi-Xin Zou Chen Wang Yan-Pei Cao and Song-Hai Zhang. 2023. threestudio: A unified framework for 3D content generation. https:\/\/github.com\/threestudio-project\/threestudio."},{"key":"e_1_3_2_1_8_1","volume-title":"3dgen: Triplane latent diffusion for textured mesh generation. arXiv preprint arXiv:2303.05371","author":"Gupta Anchit","year":"2023","unstructured":"Anchit Gupta, Wenhan Xiong, Yixin Nie, Ian Jones, and Barlas O\u011fuz. 2023. 3dgen: Triplane latent diffusion for textured mesh generation. arXiv preprint arXiv:2303.05371 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"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":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_1_12_1","volume-title":"A Survey On Text-to-3D Contents Generation In The Wild. arXiv e-prints","author":"Jiang Chenhan","year":"2024","unstructured":"Chenhan Jiang. 2024. A Survey On Text-to-3D Contents Generation In The Wild. arXiv e-prints (2024), arXiv-2405."},{"key":"e_1_3_2_1_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on learning representations (ICLR)","volume":"5","author":"Kinga D","year":"2015","unstructured":"D Kinga, Jimmy Ba Adam, et al., 2015. A method for stochastic optimization. In International conference on learning representations (ICLR), Vol. 5. San Diego, California;, 6."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8744-8753","author":"Lu Yuanxun","year":"2024","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 2.5 d diffusion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8744-8753."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"e_1_3_2_1_22_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_23_1","volume-title":"DreamFusion: Text-to-3D using 2D Diffusion. arXiv","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 (2022)."},{"key":"e_1_3_2_1_24_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","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 ICML. PMLR, 8748-8763.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_25_1","volume-title":"Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501","author":"Ravi Nikhila","year":"2020","unstructured":"Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari. 2020. Accelerating 3D Deep Learning with PyTorch3D. arXiv:2007.08501 (2020)."},{"key":"e_1_3_2_1_26_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems Vol. 35 (2022) 25278-25294."},{"key":"e_1_3_2_1_27_1","unstructured":"Jiaxiang Tang Jiawei Ren Hang Zhou Ziwei Liu and Gang Zeng. 2024. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. In ICLR."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. PMLR, 54015-54029","author":"Wu Haoning","year":"2024","unstructured":"Haoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Yixuan Gao, Annan Wang, Erli Zhang, Wenxiu Sun, et al., 2024b. Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels. In International Conference on Machine Learning. PMLR, 54015-54029."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"e_1_3_2_1_33_1","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","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. Advances in Neural Information Processing Systems, Vol. 36 (2023), 15903-15935.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","unstructured":"Xianghui Yang Huiwen Shi Bowen Zhang Fan Yang Jiacheng Wang Hongxu Zhao Xinhai Liu Xinzhou Wang Qingxiang Lin Jiaao Yu et al. 2024. Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation. arXiv preprint arXiv:2411.02293 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"e_1_3_2_1_36_1","volume-title":"Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation. arXiv preprint arXiv:2412.11170","author":"Zhang Yujie","year":"2024","unstructured":"Yujie Zhang, Bingyang Cui, Qi Yang, Zhu Li, and Yiling Xu. 2024. Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation. arXiv preprint arXiv:2412.11170 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:07Z","timestamp":1765309567000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758302"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":36,"alternative-id":["10.1145\/3746027.3758302","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758302","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}