{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:12:09Z","timestamp":1784268729794,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657417","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3267-6040","authenticated-orcid":false,"given":"Boming","family":"Zhao","sequence":"first","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4267-7297","authenticated-orcid":false,"given":"Yuan","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2740-4058","authenticated-orcid":false,"given":"Ziyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Jilin University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6770-4057","authenticated-orcid":false,"given":"Lin","family":"Zeng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3801-6705","authenticated-orcid":false,"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3477-1466","authenticated-orcid":false,"given":"Rui","family":"Ma","sequence":"additional","affiliation":[{"name":"Jilin University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5386-8872","authenticated-orcid":false,"given":"Yinda","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Inc., United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2662-0334","authenticated-orcid":false,"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7130-439X","authenticated-orcid":false,"given":"Zhaopeng","family":"Cui","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01594"},{"key":"e_1_3_2_2_3_1","volume-title":"Stochastic variational video prediction. arXiv preprint arXiv:1710.11252","author":"Babaeizadeh Mohammad","year":"2017","unstructured":"Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy\u00a0H Campbell, and Sergey Levine. 2017. Stochastic variational video prediction. arXiv preprint arXiv:1710.11252 (2017)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00541"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392485"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00702"},{"key":"e_1_3_2_2_10_1","volume-title":"International conference on machine learning. PMLR, 1174\u20131183","author":"Denton Emily","year":"2018","unstructured":"Emily Denton and Rob Fergus. 2018. Stochastic video generation with a learned prior. In International conference on machine learning. PMLR, 1174\u20131183."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925969"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01406"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/83.623193"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555383"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555383"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00846"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"e_1_3_2_2_20_1","volume-title":"Diffusion models for video prediction and infilling. arXiv preprint arXiv:2206.07696","author":"H\u00f6ppe Tobias","year":"2022","unstructured":"Tobias H\u00f6ppe, Arash Mehrjou, Stefan Bauer, Didrik Nielsen, and Andrea Dittadi. 2022. Diffusion models for video prediction and infilling. arXiv preprint arXiv:2206.07696 (2022)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01807"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00416"},{"key":"e_1_3_2_2_27_1","volume-title":"Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes. arXiv preprint arXiv:2310.08585","author":"Lin Haotong","year":"2023","unstructured":"Haotong Lin, Sida Peng, Zhen Xu, Tao Xie, Xingyi He, Hujun Bao, and Xiaowei Zhou. 2023. Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes. arXiv preprint arXiv:2310.08585 (2023)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555376"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00010"},{"key":"e_1_3_2_2_30_1","volume-title":"Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751","author":"Lombardi Stephen","year":"2019","unstructured":"Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, and Yaser Sheikh. 2019. Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751 (2019)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459863"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.230"},{"key":"e_1_3_2_2_33_1","volume-title":"Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713","author":"Luiten Jonathon","year":"2023","unstructured":"Jonathon Luiten, Georgios Kopanas, Bastian Leibe, and Deva Ramanan. 2023. Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713 (2023)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00958"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"e_1_3_2_2_36_1","volume-title":"Conference on Robot Learning. PMLR, 1444\u20131454","author":"Mersch Benedikt","year":"2022","unstructured":"Benedikt Mersch, Xieyuanli Chen, Jens Behley, and Cyrill Stachniss. 2022. Self-supervised point cloud prediction using 3d spatio-temporal convolutional networks. In Conference on Robot Learning. PMLR, 1444\u20131454."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045007"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984517"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"e_1_3_2_2_44_1","volume-title":"Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228","author":"Park Keunhong","year":"2021","unstructured":"Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan\u00a0T Barron, Sofien Bouaziz, Dan\u00a0B Goldman, Ricardo Martin-Brualla, and Steven\u00a0M Seitz. 2021b. Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228 (2021)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00414"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01596"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01102"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247082"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"e_1_3_2_2_55_1","volume-title":"International Conference on Machine Learning. PMLR, 6038\u20136046","author":"Villegas Ruben","year":"2018","unstructured":"Ruben Villegas, Dumitru Erhan, Honglak Lee, 2018. Hierarchical long-term video prediction without supervision. In International Conference on Machine Learning. PMLR, 6038\u20136046."},{"key":"e_1_3_2_2_56_1","volume-title":"Generating videos with scene dynamics. Advances in neural information processing systems 29","author":"Vondrick Carl","year":"2016","unstructured":"Carl Vondrick, Hamed Pirsiavash, and Antonio Torralba. 2016. Generating videos with scene dynamics. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_2_57_1","volume-title":"International conference on learning representations.","author":"Wang Yunbo","year":"2018","unstructured":"Yunbo Wang, Lu Jiang, Ming-Hsuan Yang, Li-Jia Li, Mingsheng Long, and Li Fei-Fei. 2018. Eidetic 3D LSTM: A model for video prediction and beyond. In International conference on learning representations."},{"key":"e_1_3_2_2_58_1","volume-title":"Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence. arXiv preprint arXiv:2312.08054","author":"Wang Zifan","year":"2023","unstructured":"Zifan Wang, Zhuorui Ye, Haoran Wu, Junyu Chen, and Li Yi. 2023. Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence. arXiv preprint arXiv:2312.08054 (2023)."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"e_1_3_2_2_60_1","volume-title":"4d gaussian splatting for real-time dynamic scene rendering. arXiv preprint arXiv:2310.08528","author":"Wu Guanjun","year":"2023","unstructured":"Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian, and Xinggang Wang. 2023. 4d gaussian splatting for real-time dynamic scene rendering. arXiv preprint arXiv:2310.08528 (2023)."},{"key":"e_1_3_2_2_61_1","volume-title":"4k4d: Real-time 4d view synthesis at 4k resolution. arXiv preprint arXiv:2310.11448","author":"Xu Zhen","year":"2023","unstructured":"Zhen Xu, Sida Peng, Haotong Lin, Guangzhao He, Jiaming Sun, Yujun Shen, Hujun Bao, and Xiaowei Zhou. 2023. 4k4d: Real-time 4d view synthesis at 4k resolution. arXiv preprint arXiv:2310.11448 (2023)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/e25101469"},{"key":"e_1_3_2_2_63_1","volume-title":"Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101","author":"Yang Ziyi","year":"2023","unstructured":"Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, and Xiaogang Jin. 2023a. Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101 (2023)."},{"key":"e_1_3_2_2_64_1","volume-title":"Real-time photorealistic dynamic scene representation and rendering with 4d gaussian splatting. arXiv preprint arXiv:2310.10642","author":"Yang Zeyu","year":"2023","unstructured":"Zeyu Yang, Hongye Yang, Zijie Pan, Xiatian Zhu, and Li Zhang. 2023c. Real-time photorealistic dynamic scene representation and rendering with 4d gaussian splatting. arXiv preprint arXiv:2310.10642 (2023)."},{"key":"e_1_3_2_2_65_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5336\u20135345","author":"Yoon Jae\u00a0Shin","year":"2020","unstructured":"Jae\u00a0Shin Yoon, Kihwan Kim, Orazio Gallo, Hyun\u00a0Soo Park, and Jan Kautz. 2020. Novel view synthesis of dynamic scenes with globally coherent depths from a monocular camera. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5336\u20135345."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555413"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00804"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00444"}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657417","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:36Z","timestamp":1750295376000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":69,"alternative-id":["10.1145\/3641519.3657417","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657417","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}