{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:41:03Z","timestamp":1777498863011,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62325206, 62206132"],"award-info":[{"award-number":["No.62325206, 62206132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Key Research and Development Program of Jiangsu Province","award":["BE2023016-4"],"award-info":[{"award-number":["BE2023016-4"]}]},{"name":"the Nanjing Scientific and Technological Innovation Project for Overseas Returnees"},{"name":"the Postgraduate Research and Practice Innovation Program of Jiangsu Province","award":["KYCX23_1023"],"award-info":[{"award-number":["KYCX23_1023"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754728","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"9296-9305","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["D\n                    <sup>2<\/sup>\n                    Gaussian: Dynamic Control with Discretized 3D View Modeling for Text-Driven 3D Gaussian Splatting Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2547-4646","authenticated-orcid":false,"given":"Yefei","family":"Sheng","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, NanJing, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8662-9488","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4662-7170","authenticated-orcid":false,"given":"Ming","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts And Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01197"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"e_1_3_2_1_8_1","volume-title":"V3d: Video Diffusion Models are Effective 3D Generators. arXiv preprint arXiv:2403.06738","author":"Chen Zilong","year":"2024","unstructured":"Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, and Huaping Liu. 2024b. V3d: Video Diffusion Models are Effective 3D Generators. arXiv preprint arXiv:2403.06738 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00645"},{"key":"e_1_3_2_1_10_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dong Jiahua","year":"2024","unstructured":"Jiahua Dong and Yu-Xiong Wang. 2024. Vica-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"An Image is Worth One Word: Personalizing Text-to-Image Generation Using Textual Inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An Image is Worth One Word: Personalizing Text-to-Image Generation Using Textual Inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_1_12_1","first-page":"75468","article-title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","volume":"37","author":"Gao Ruiqi","year":"2025","unstructured":"Ruiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee, Ricardo Martin Brualla, Pratul Srinivasan, Jonathan Barron, and Ben Poole. 2025. CAT3D: Create Anything in 3D with Multi-View Diffusion Models. Advances in Neural Information Processing Systems, Vol. 37 (2025), 75468-75494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"e_1_3_2_1_14_1","volume-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations.","author":"Hertz Amir","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-or. [n.d.]. Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_16_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_17_1","volume-title":"Instruct 3d-to-3d: Text instruction guided 3d-to-3d conversion. arXiv preprint arXiv:2303.15780","author":"Kamata Hiromichi","year":"2023","unstructured":"Hiromichi Kamata, Yuiko Sakuma, Akio Hayakawa, Masato Ishii, and Takuya Narihira. 2023. Instruct 3d-to-3d: Text instruction guided 3d-to-3d conversion. arXiv preprint arXiv:2303.15780 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647415"},{"key":"e_1_3_2_1_24_1","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_26_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_27_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems Vol. 35 (2022) 27730-27744."},{"key":"e_1_3_2_1_28_1","volume-title":"Styleclip: Text-driven manipulation of stylegan imagery.","author":"Patashnik Or","year":"2021","unstructured":"Or Patashnik, Zongze Wu, Eli Shechtman, Daniel Cohen-Or, and Dani Lischinski. 2021. Styleclip: Text-driven manipulation of stylegan imagery. (2021), 2085-2094."},{"key":"e_1_3_2_1_29_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_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730600"},{"key":"e_1_3_2_1_31_1","unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_1_33_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_36_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479-36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"ConsistentDreamer: View-Consistent Meshes Through Balanced Multi-View Gaussian Optimization. arXiv preprint arXiv:2502.09278","author":"Onat","year":"2025","unstructured":"Onat ?ahin, Mohammad Altillawi, George Eskandar, Carlos Carbone, and Ziyuan Liu. 2025. ConsistentDreamer: View-Consistent Meshes Through Balanced Multi-View Gaussian Optimization. arXiv preprint arXiv:2502.09278 (2025)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"e_1_3_2_1_39_1","volume-title":"Imagine, Select, and Fuse with GPT-Based Text Enrichment for Text-to-Image Synthesis. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Sheng Yefei","year":"2024","unstructured":"Yefei Sheng, Ming Tao, Jie Wang, and Bing-Kun Bao. 2024. ISF-GAN: Imagine, Select, and Fuse with GPT-Based Text Enrichment for Text-to-Image Synthesis. ACM Transactions on Multimedia Computing, Communications and Applications (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"e_1_3_2_1_43_1","volume-title":"Nerf-art: Text-driven neural radiance fields stylization","author":"Wang Can","year":"2023","unstructured":"Can Wang, Ruixiang Jiang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. 2023. Nerf-art: Text-driven neural radiance fields stylization. IEEE Transactions on Visualization and Computer Graphics (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation. arXiv preprint arXiv:2312.02201","author":"Wang Peng","year":"2023","unstructured":"Peng Wang and Yichun Shi. 2023. Imagedream: Image-prompt multi-view diffusion for 3d generation. arXiv preprint arXiv:2312.02201 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Zhengyi","year":"2024","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2024. Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"GaussCtrl: multi-view consistent text-driven 3D Gaussian splatting editing. arXiv preprint arXiv:2403.08733","author":"Wu Jing","year":"2024","unstructured":"Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, and Victor Adrian Prisacariu. 2024. GaussCtrl: multi-view consistent text-driven 3D Gaussian splatting editing. arXiv preprint arXiv:2403.08733 (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"Yi-Ping Phoebe Chen, and Changsheng Xu","author":"Yuan Bowen","year":"2023","unstructured":"Bowen Yuan, Yefei Sheng, Bing-Kun Bao, Yi-Ping Phoebe Chen, and Changsheng Xu. 2023. Semantic Distance Adversarial Learning for Text-to-Image Synthesis. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618190"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2001.964490"}],"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\/3746027.3754728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:06:35Z","timestamp":1765343195000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3754728","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754728","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"}}]}}