{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:05:09Z","timestamp":1778083509100,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"Fundamental Research Funds for the Provincial Universities of Zhejiang","award":["GK259909299001-044"],"award-info":[{"award-number":["GK259909299001-044"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306253"],"award-info":[{"award-number":["62306253"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Fund-General Program","award":["2024A1515010233"],"award-info":[{"award-number":["2024A1515010233"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755516","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"8478-8487","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8250-0030","authenticated-orcid":false,"given":"Zhicong","family":"Wu","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3455-1527","authenticated-orcid":false,"given":"Hongbin","family":"Xu","sequence":"additional","affiliation":[{"name":"Bytedance Seed, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9159-4662","authenticated-orcid":false,"given":"Gang","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4260-879X","authenticated-orcid":false,"given":"Ping","family":"Nie","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4402-2677","authenticated-orcid":false,"given":"Zhixin","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Future Technology, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9176-7703","authenticated-orcid":false,"given":"Jinkai","family":"Zheng","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China and Central Laboratory of Lishui Hospital of Wenzhou Medical University, The First Affiliated Hospital of Lishui University, Lishui People's Hospital, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8235-7852","authenticated-orcid":false,"given":"Liangqiong","family":"Qu","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7852-0159","authenticated-orcid":false,"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), 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":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"e_1_3_2_1_4_1","volume-title":"Explicit correspondence matching for generalizable neural radiance fields. arXiv preprint arXiv:2304.12294","author":"Chen Yuedong","year":"2023","unstructured":"Yuedong Chen, Haofei Xu, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, and Jianfei Cai. 2023. Explicit correspondence matching for generalizable neural radiance fields. arXiv preprint arXiv:2304.12294 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"European Conference on Computer Vision. Springer, 370-386","author":"Chen Yuedong","year":"2024","unstructured":"Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, and Jianfei Cai. 2024b. Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images. In European Conference on Computer Vision. Springer, 370-386."},{"key":"e_1_3_2_1_6_1","volume-title":"Mvsplat360: Feed-forward 360 scene synthesis from sparse views. arXiv preprint arXiv:2411.04924","author":"Chen Yuedong","year":"2024","unstructured":"Yuedong Chen, Chuanxia Zheng, Haofei Xu, Bohan Zhuang, Andrea Vedaldi, Tat-Jen Cham, and Jianfei Cai. 2024c. Mvsplat360: Feed-forward 360 scene synthesis from sparse views. arXiv preprint arXiv:2411.04924 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3354108"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Yasutaka Furukawa Carlos Hern\u00e1ndez et al. 2015. Multi-view stereo: A tutorial. Foundations and trends\u00ae in Computer Graphics and Vision Vol. 9 1-2 (2015) 1-148.","DOI":"10.1561\/0600000052"},{"key":"e_1_3_2_1_11_1","volume-title":"Cat3d: Create anything in 3d with multi-view diffusion models. arXiv preprint arXiv:2405.10314","author":"Gao Ruiqi","year":"2024","unstructured":"Ruiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee, Ricardo Martin-Brualla, Pratul Srinivasan, Jonathan T Barron, and Ben Poole. 2024. Cat3d: Create anything in 3d with multi-view diffusion models. arXiv preprint arXiv:2405.10314 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01317"},{"key":"e_1_3_2_1_15_1","volume-title":"Moganet: Multi-order gated aggregation network. arXiv preprint arXiv:2211.03295","author":"Li Siyuan","year":"2022","unstructured":"Siyuan Li, Zedong Wang, Zicheng Liu, Cheng Tan, Haitao Lin, Di Wu, Zhiyuan Chen, Jiangbin Zheng, and Stan Z Li. 2022. Moganet: Multi-order gated aggregation network. arXiv preprint arXiv:2211.03295 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"e_1_3_2_1_17_1","volume-title":"Phys4dgen: A physics-driven framework for controllable and efficient 4d content generation from a single image. arXiv e-prints","author":"Lin Jiajing","year":"2024","unstructured":"Jiajing Lin, Zhenzhong Wang, Shu Jiang, Yongjie Hou, and Min Jiang. 2024. Phys4dgen: A physics-driven framework for controllable and efficient 4d content generation from a single image. arXiv e-prints (2024), arXiv-2411."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_21_1","volume-title":"Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG)","author":"M\u00fcller Thomas","year":"2022","unstructured":"Thomas M\u00fcller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG), Vol. 41, 4 (2022), 1-15."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"e_1_3_2_1_23_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703","author":"Paszke A","year":"2019","unstructured":"A Paszke. 2019. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)."},{"key":"e_1_3_2_1_24_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_25_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_27_1","first-page":"234","volume-title":"Munich","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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_10"},{"key":"e_1_3_2_1_30_1","volume-title":"Flash3d: Feed-forward generalisable 3d scene reconstruction from a single image. arXiv preprint arXiv:2406.04343","author":"Szymanowicz Stanislaw","year":"2024","unstructured":"Stanislaw Szymanowicz, Eldar Insafutdinov, Chuanxia Zheng, Dylan Campbell, Joao F Henriques, Christian Rupprecht, and Andrea Vedaldi. 2024. Flash3d: Feed-forward generalisable 3d scene reconstruction from a single image. arXiv preprint arXiv:2406.04343 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Hisplat: Hierarchical 3d gaussian splatting for generalizable sparse-view reconstruction. arXiv preprint arXiv:2410.06245","author":"Tang Shengji","year":"2024","unstructured":"Shengji Tang, Weicai Ye, Peng Ye, Weihao Lin, Yang Zhou, Tao Chen, and Wanli Ouyang. 2024. Hisplat: Hierarchical 3d gaussian splatting for generalizable sparse-view reconstruction. arXiv preprint arXiv:2410.06245 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00408"},{"key":"e_1_3_2_1_33_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2021.102102"},{"key":"e_1_3_2_1_35_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600-612."},{"key":"e_1_3_2_1_36_1","volume-title":"Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction. arXiv preprint arXiv:2412.06273","author":"Wei Dongxu","year":"2024","unstructured":"Dongxu Wei, Zhiqi Li, and Peidong Liu. 2024. Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction. arXiv preprint arXiv:2412.06273 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01894"},{"key":"e_1_3_2_1_39_1","volume-title":"Depthsplat: Connecting gaussian splatting and depth. arXiv preprint arXiv:2410.13862","author":"Xu Haofei","year":"2024","unstructured":"Haofei Xu, Songyou Peng, Fangjinhua Wang, Hermann Blum, Daniel Barath, Andreas Geiger, and Marc Pollefeys. 2024b. Depthsplat: Connecting gaussian splatting and depth. arXiv preprint arXiv:2410.13862 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_1_43_1","volume-title":"Transplat: Generalizable 3d gaussian splatting from sparse multi-view images with transformers. arXiv preprint arXiv:2408.13770","author":"Zhang Chuanrui","year":"2024","unstructured":"Chuanrui Zhang, Yingshuang Zou, Zhuoling Li, Minmin Yi, and Haoqian Wang. 2024b. Transplat: Generalizable 3d gaussian splatting from sparse multi-view images with transformers. arXiv preprint arXiv:2408.13770 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"European Conference on Computer Vision. Springer, 1-19","author":"Zhang Kai","year":"2024","unstructured":"Kai Zhang, Sai Bi, Hao Tan, Yuanbo Xiangli, Nanxuan Zhao, Kalyan Sunkavalli, and Zexiang Xu. 2024a. Gs-lrm: Large reconstruction model for 3d gaussian splatting. In European Conference on Computer Vision. Springer, 1-19."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"e_1_3_2_1_47_1","volume-title":"Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817","author":"Zhou Tinghui","year":"2018","unstructured":"Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, and Noah Snavely. 2018. Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3360710"}],"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\/3746027.3755516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:23:11Z","timestamp":1765308191000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3755516","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755516","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"}}]}}