{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:24Z","timestamp":1781538924554,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62077026"],"award-info":[{"award-number":["62077026"]}]},{"name":"National Key Research and Development Program of China","award":["2024YFC3308300"],"award-info":[{"award-number":["2024YFC3308300"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810719","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1394-1403","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["STAR-GS: Spatio-Temporal Geometry Alignment and Generative Refinement for Sparse-View 4D Gaussian Splatting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4194-665X","authenticated-orcid":false,"given":"Yunqi","family":"Gao","sequence":"first","affiliation":[{"name":"Central China Normal University, Wuhan, -Select-, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3337-3993","authenticated-orcid":false,"given":"Zhanfeng","family":"Liao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8682-6281","authenticated-orcid":false,"given":"Dongbo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Central China Normal University, Wuhan, Hebei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8050-8677","authenticated-orcid":false,"given":"Leyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Central China Normal University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_42"},{"key":"e_1_3_3_2_3_2","first-page":"321","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Bae Jeongmin","year":"2024","unstructured":"Jeongmin Bae, Seoha Kim, Youngsik Yun, Hahyun Lee, Gun Bang, and Youngjung Uh. 2024. Per-gaussian embedding-based deformation for deformable 3d gaussian splatting. In Eur. Conf. Comput. Vis. (ECCV). Springer, 321\u2013335."},{"key":"e_1_3_3_2_4_2","volume-title":"Int. Conf. Learn. Represent.","author":"Bai Jianhong","year":"2025","unstructured":"Jianhong Bai, Menghan Xia, Xintao Wang, Ziyang Yuan, Zuozhu Liu, Haoji Hu, Pengfei Wan, and Di ZHANG. 2025. SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints. In Int. Conf. Learn. Represent."},{"key":"e_1_3_3_2_5_2","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et\u00a0al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15127 (2023)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32193"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Danpeng Chen Hai Li Weicai Ye Yifan Wang Weijian Xie Shangjin Zhai Nan Wang Haomin Liu Hujun Bao and Guofeng Zhang. 2024. PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction. IEEE Trans. Vis. Comput. Graph. 31 9 (2024) 6100\u20136111.","DOI":"10.1109\/TVCG.2024.3494046"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657463"},{"key":"e_1_3_3_2_9_2","unstructured":"Zhongpai Gao Benjamin Planche Meng Zheng Anwesa Choudhuri Terrence Chen and Ziyan Wu. 2025. 7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.07946 (2025)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"e_1_3_3_2_11_2","unstructured":"Zhiyang Guo Wengang Zhou Li Li Min Wang and Houqiang Li. 2024. Motion-aware 3d gaussian splatting for efficient dynamic scene reconstruction. (2024)."},{"key":"e_1_3_3_2_12_2","series-title":"(NIPS \u201924)","volume-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Han Liang","year":"2025","unstructured":"Liang Han, Junsheng Zhou, Yu-Shen Liu, and Zhizhong Han. 2025. Binocular-guided 3D Gaussian splatting with view consistency for sparse view synthesis. In Adv. Neural Inform. Process. Syst. (NeurIPS) (Vancouver, BC, Canada) (NIPS \u201924). Curran Associates Inc., Red Hook, NY, USA, Article 2191, 27\u00a0pages."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Yuhang Hong Bo Tao and Zeyu Gong. 2025. ShareGS: Hole completion with sparse inputs based on reusing selected scene information. Pattern Recognition (2025) 111729.","DOI":"10.1016\/j.patcog.2025.111729"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755819"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32379"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (TOG) 42 4 (2023) 1\u201314.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Mijeong Kim Jongwoo Lim and Bohyung Han. 2024. 4d gaussian splatting in the wild with uncertainty-aware regularization. Advances in Neural Information Processing Systems 37 (2024) 129209\u2013129226.","DOI":"10.52202\/079017-4104"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Junoh Lee ChangYeon Won Hyunjun Jung Inhwan Bae and Hae-Gon Jeon. 2024. Fully explicit dynamic gaussian splatting. Advances in Neural Information Processing Systems 37 (2024) 5384\u20135409.","DOI":"10.52202\/079017-0174"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00578"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"e_1_3_3_2_23_2","unstructured":"Yangming Li Chaoyu Liu Lihao Liu Simon Masnou and Carola-Bibiane Sch\u00f6nlieb. 2025. GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.05075 (2025)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Yiqing Liang Numair Khan Zhengqin Li Thu Nguyen-Phuoc Douglas Lanman James Tompkin and Lei Xiao. 2025. Gaufre: Gaussian deformation fields for real-time dynamic novel view synthesis. IEEE 2642\u20132652.","DOI":"10.1109\/WACV61041.2025.00262"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00850"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Ben Mildenhall Pratul\u00a0P. Srinivasan Matthew Tancik Jonathan\u00a0T. Barron Ravi Ramamoorthi and Ren Ng. 2021. NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (Dec. 2021) 99\u2013106. 10.1145\/3503250","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_2_29_2","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Paliwal Avinash","year":"2024","unstructured":"Avinash Paliwal, Wei Ye, Jinhui Xiong, Dmytro Kotovenko, Rakesh Ranjan, Vikas Chandra, and Nima\u00a0Khademi Kalantari. 2024. CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians. In Eur. Conf. Comput. Vis. (ECCV)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02012"},{"key":"e_1_3_3_2_31_2","volume-title":"Int. Conf. Learn. Represent.","author":"Qingming LIU","year":"2025","unstructured":"LIU Qingming, Yuan Liu, Jiepeng Wang, Xianqiang Lyu, Peng Wang, Wenping Wang, and Junhui Hou. 2025. MoDGS: Dynamic gaussian splatting from casually-captured monocular videos with depth priors. In Int. Conf. Learn. Represent."},{"key":"e_1_3_3_2_32_2","first-page":"347","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Rota\u00a0Bul\u00f2 Samuel","year":"2024","unstructured":"Samuel Rota\u00a0Bul\u00f2, Lorenzo Porzi, and Peter Kontschieder. 2024. Revising densification in gaussian splatting. In Eur. Conf. Comput. Vis. (ECCV). Springer, 347\u2013362."},{"key":"e_1_3_3_2_33_2","unstructured":"Abhishek Saroha Florian Hofherr Mariia Gladkova Cecilia Curreli Or Litany and Daniel Cremers. 2025. ZDySS\u2013Zero-Shot Dynamic Scene Stylization using Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03875 (2025)."},{"key":"e_1_3_3_2_34_2","first-page":"87","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Sauer Axel","year":"2024","unstructured":"Axel Sauer, Dominik Lorenz, Andreas Blattmann, and Robin Rombach. 2024. Adversarial diffusion distillation. In Eur. Conf. Comput. Vis. (ECCV). Springer, 87\u2013103."},{"key":"e_1_3_3_2_35_2","first-page":"37","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Shaw Richard","year":"2024","unstructured":"Richard Shaw, Michal Nazarczuk, Jifei Song, Arthur Moreau, Sibi Catley-Chandar, Helisa Dhamo, and Eduardo P\u00e9rez-Pellitero. 2024. Swings: sliding windows for dynamic 3d gaussian splatting. In Eur. Conf. Comput. Vis. (ECCV). Springer, 37\u201354."},{"key":"e_1_3_3_2_36_2","unstructured":"Oriane Sim\u00e9oni Huy\u00a0V. Vo Maximilian Seitzer Federico Baldassarre Maxime Oquab Cijo Jose Vasil Khalidov Marc Szafraniec Seungeun Yi Micha\u00ebl Ramamonjisoa Francisco Massa Daniel Haziza Luca Wehrstedt Jianyuan Wang Timoth\u00e9e Darcet Th\u00e9o Moutakanni Leonel Sentana Claire Roberts Andrea Vedaldi Jamie Tolan John Brandt Camille Couprie Julien Mairal Herv\u00e9 J\u00e9gou Patrick Labatut and Piotr Bojanowski. 2025. DINOv3. arxiv:https:\/\/arXiv.org\/abs\/2508.10104\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2508.10104"},{"key":"e_1_3_3_2_37_2","volume-title":"3rd International Conference on Learning Representations (ICLR 2015)","author":"Simonyan K","year":"2015","unstructured":"K Simonyan and A Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations (ICLR 2015). Computational and Biological Learning Society."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01954"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Carlo Tomasi and Takeo Kanade. 1992. Shape and motion from image streams under orthography: a factorization method. International journal of computer vision 9 2 (1992) 137\u2013154.","DOI":"10.1007\/BF00129684"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Shimon Ullman. 1979. The interpretation of structure from motion. Proceedings of the Royal Society of London. Series B. Biological Sciences 203 1153 (1979) 405\u2013426.","DOI":"10.1098\/rspb.1979.0006"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02026"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Zhou Wang A.C. Bovik H.R. Sheikh and E.P. Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. (TIP) 13 4 (2004) 600\u2013612. 10.1109\/TIP.2003.819861","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00773"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01056"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02424"},{"key":"e_1_3_3_2_47_2","unstructured":"Renlong Wu Zhilu Zhang Mingyang Chen Zifei Yan and Wangmeng Zuo. 2024. Deblur4dgs: 4d gaussian splatting from blurry monocular video. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.06424 (2024)."},{"key":"e_1_3_3_2_48_2","unstructured":"Haolin Xiong Sairisheek Muttukuru Rishi Upadhyay Pradyumna Chari and Achuta Kadambi. 2023. Sparsegs: Real-time 360 {\\ deg} sparse view synthesis using gaussian splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.00206 (2023)."},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Jiawei Xu Zexin Fan Jian Yang and Jin Xie. 2024. Grid4d: 4d decomposed hash encoding for high-fidelity dynamic gaussian splatting. Advances in Neural Information Processing Systems 37 (2024) 123787\u2013123811.","DOI":"10.52202\/079017-3934"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01893"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Zhen Xu Yinghao Xu Zhiyuan Yu Sida Peng Jiaming Sun Hujun Bao and Xiaowei Zhou. 2024. Representing long volumetric video with temporal gaussian hierarchy. ACM Trans. Graph. (TOG) 43 6 (2024) 1\u201318.","DOI":"10.1145\/3687919"},{"key":"e_1_3_3_2_52_2","unstructured":"Yuxue Yang Lue Fan Ziqi Shi Junran Peng Feng Wang and Zhaoxiang Zhang. 2026. NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.00393 (2026)."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"e_1_3_3_2_54_2","volume-title":"ICLR","author":"Yang Zeyu","year":"2024","unstructured":"Zeyu Yang, Hongye Yang, Zijie Pan, and Li Zhang. 2024. Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting. In ICLR."},{"key":"e_1_3_3_2_55_2","first-page":"162","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Ye Mingqiao","year":"2024","unstructured":"Mingqiao Ye, Martin Danelljan, Fisher Yu, and Lei Ke. 2024. Gaussian grouping: Segment and edit anything in 3d scenes. In Eur. Conf. Comput. Vis. (ECCV). Springer, 162\u2013179."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681361"},{"key":"e_1_3_3_2_57_2","unstructured":"Xingyilang Yin Qi Zhang Jiahao Chang Ying Feng Qingnan Fan Xi Yang Chi-Man Pun Huaqi Zhang and Xiaodong Cun. 2025. Gsfixer: Improving 3d gaussian splatting with reference-guided video diffusion priors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.09667 (2025)."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Zehao Yu Torsten Sattler and Andreas Geiger. 2024. Gaussian opacity fields: Efficient adaptive surface reconstruction in unbounded scenes. ACM Trans. Graph. (TOG) 43 6 (2024) 1\u201313.","DOI":"10.1145\/3687937"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_19"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"e_1_3_3_2_63_2","first-page":"101790","volume-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Zhu Ruijie","year":"2024","unstructured":"Ruijie Zhu, Yanzhe Liang, Hanzhi Chang, Jiacheng Deng, Jiahao Lu, Wenfei Yang, Tianzhu Zhang, and Yongdong Zhang. 2024. Motiongs: Exploring explicit motion guidance for deformable 3d gaussian splatting. In Adv. Neural Inform. Process. Syst. (NeurIPS) , Vol.\u00a037. 101790\u2013101817."},{"key":"e_1_3_3_2_64_2","first-page":"145","volume-title":"Eur. Conf. Comput. Vis. (ECCV)","author":"Zhu Zehao","year":"2024","unstructured":"Zehao Zhu, Zhiwen Fan, Yifan Jiang, and Zhangyang Wang. 2024. FSGS: Real-time few-shot view synthesis using gaussian splatting. In Eur. Conf. Comput. Vis. (ECCV). Springer, 145\u2013163."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:18:34Z","timestamp":1781536714000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":63,"alternative-id":["10.1145\/3805622.3810719","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810719","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}