{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:00:05Z","timestamp":1774022405538,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730757","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:42:43Z","timestamp":1753260163000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2650-4555","authenticated-orcid":false,"given":"Zinuo","family":"You","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4749-7339","authenticated-orcid":false,"given":"Stamatios","family":"Georgoulis","sequence":"additional","affiliation":[{"name":"Huawei Research Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2150-2176","authenticated-orcid":false,"given":"Anpei","family":"Chen","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland and University of T\u00fcbingen, T\u00fcbingen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1015-4770","authenticated-orcid":false,"given":"Siyu","family":"Tang","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5440-9678","authenticated-orcid":false,"given":"Dengxin","family":"Dai","sequence":"additional","affiliation":[{"name":"Huawei Research Z\u00fcrich, Z\u00fcrich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01198"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00108"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"crossref","unstructured":"Yuedong Chen Haofei Xu Chuanxia Zheng Bohan Zhuang Marc Pollefeys Andreas Geiger Tat-Jen Cham and Jianfei Cai. 2024. Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.14627 (2024).","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506801"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00782"},{"key":"e_1_3_3_3_9_1","unstructured":"Woong\u00a0Oh Cho In Cho Seoha Kim Jeongmin Bae Youngjung Uh and Seon\u00a0Joo Kim. 2024. 4D Scaffold Gaussian Splatting for Memory Efficient Dynamic Scene Reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17044 (2024)."},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"crossref","unstructured":"Jinsoo Choi and In\u00a0So Kweon. 2020. Deep iterative frame interpolation for full-frame video stabilization. ACM Transactions on Graphics (TOG) 39 1 (2020) 1\u20139.","DOI":"10.1145\/3363550"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"crossref","unstructured":"Amit Goldstein and Raanan Fattal. 2012. Video stabilization using epipolar geometry. ACM Transactions on Graphics (TOG) 31 5 (2012) 1\u201310.","DOI":"10.1145\/2231816.2231824"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995525"},{"key":"e_1_3_3_3_14_1","unstructured":"Wenbo Hu Xiangjun Gao Xiaoyu Li Sijie Zhao Xiaodong Cun Yong Zhang Long Quan and Ying Shan. 2024. Depthcrafter: Generating consistent long depth sequences for open-world videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.02095 (2024)."},{"key":"e_1_3_3_3_15_1","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. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"crossref","unstructured":"Yeong\u00a0Jun Koh Chulwoo Lee and Chang-Su Kim. 2015. Video stabilization based on feature trajectory augmentation and selection and robust mesh grid warping. IEEE Transactions on Image Processing 24 12 (2015) 5260\u20135273.","DOI":"10.1109\/TIP.2015.2479918"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459297"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01048"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"crossref","unstructured":"Chen Li Li Song Shuai Chen Rong Xie and Wenjun Zhang. 2022. Deep online video stabilization using imu sensors. IEEE Transactions on Multimedia 25 (2022) 2047\u20132060.","DOI":"10.1109\/TMM.2022.3142429"},{"key":"e_1_3_3_3_21_1","unstructured":"Xuanyi Li Daquan Zhou Chenxu Zhang Shaodong Wei Qibin Hou and Ming-Ming Cheng. 2024. Sora generates videos with stunning geometrical consistency. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17403 (2024)."},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596778"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Shuaicheng Liu Mingyu Li Shuyuan Zhu and Bing Zeng. 2017. Codingflow: Enable video coding for video stabilization. IEEE Transactions on Image Processing 26 7 (2017) 3291\u20133302.","DOI":"10.1109\/TIP.2017.2697759"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_48"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/CVPR.2012.6247662","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu Shuaicheng","year":"2012","unstructured":"Shuaicheng Liu, Yinting Wang, Lu Yuan, Jiajun Bu, Ping Tan, and Jian Sun. 2012. Video stabilization with a depth camera. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 89\u201395."},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"crossref","unstructured":"Shuaicheng Liu Lu Yuan Ping Tan and Jian Sun. 2013. Bundled camera paths for video stabilization. ACM transactions on graphics (TOG) 32 4 (2013) 1\u201310.","DOI":"10.1145\/2461912.2461995"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.536"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00230"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"crossref","unstructured":"Xuan Luo Jia-Bin Huang Richard Szeliski Kevin Matzen and Johannes Kopf. 2020. Consistent video depth estimation. ACM Transactions on Graphics (ToG) 39 4 (2020) 71\u20131.","DOI":"10.1145\/3386569.3392377"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00717"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"e_1_3_3_3_33_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan et\u00a0al. 2024. Grounded sam: Assembling open-world models for diverse visual tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.14159 (2024)."},{"key":"e_1_3_3_3_34_1","unstructured":"Jiahao Shao Yuanbo Yang Hongyu Zhou Youmin Zhang Yujun Shen Matteo Poggi and Yiyi Liao. 2024. Learning Temporally Consistent Video Depth from Video Diffusion Priors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.01493 (2024)."},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00094"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"crossref","unstructured":"Stanislaw Szymanowicz Eldar Insafutdinov Chuanxia Zheng Dylan Campbell Jo\u00e3o\u00a0F Henriques Christian Rupprecht and Andrea Vedaldi. 2024. Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.04343 (2024).","DOI":"10.1109\/3DV66043.2025.00067"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_19"},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"crossref","unstructured":"Miao Wang Guo-Ye Yang Jin-Kun Lin Song-Hai Zhang Ariel Shamir Shao-Ping Lu and Shi-Min Hu. 2018. Deep online video stabilization with multi-grid warping transformation learning. IEEE Transactions on Image Processing 28 5 (2018) 2283\u20132292.","DOI":"10.1109\/TIP.2018.2884280"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"e_1_3_3_3_42_1","unstructured":"Qianqian Wang Vickie Ye Hang Gao Jake Austin Zhengqi Li and Angjoo Kanazawa. 2024. Shape of Motion: 4D Reconstruction from a Single Video. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.13764 (2024)."},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00868"},{"key":"e_1_3_3_3_44_1","volume-title":"arXiv","author":"Wewer Christopher","year":"2024","unstructured":"Christopher Wewer, Kevin Raj, Eddy Ilg, Bernt Schiele, and Jan\u00a0Eric Lenssen. 2024. latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction. In arXiv."},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01894"},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"crossref","unstructured":"Yufei Xu Jing Zhang Stephen\u00a0J Maybank and Dacheng Tao. 2022. Dut: Learning video stabilization by simply watching unstable videos. IEEE Transactions on Image Processing 31 (2022) 4306\u20134320.","DOI":"10.1109\/TIP.2022.3182887"},{"key":"e_1_3_3_3_47_1","unstructured":"Honghui Yang Di Huang Wei Yin Chunhua Shen Haifeng Liu Xiaofei He Binbin Lin Wanli Ouyang and Tong He. 2024. Depth any video with scalable synthetic data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.10815 (2024)."},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01875"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_34"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00818"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00181"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02105"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"crossref","unstructured":"Minda Zhao and Qiang Ling. 2020. Pwstablenet: Learning pixel-wise warping maps for video stabilization. IEEE Transactions on Image Processing 29 (2020) 3582\u20133595.","DOI":"10.1109\/TIP.2019.2963380"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:02:26Z","timestamp":1774018946000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730757"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":54,"alternative-id":["10.1145\/3721238.3730757","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730757","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}