{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:22Z","timestamp":1784228722057,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811184","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TrajVG: 3D Trajectory-Coupled Visual Geometry Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1203-8279","authenticated-orcid":false,"given":"Xingyu","family":"Miao","sequence":"first","affiliation":[{"name":"Durham University, Durham, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6925-9876","authenticated-orcid":false,"given":"Weiguang","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8830-3820","authenticated-orcid":false,"given":"Tao","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Aritificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1026-2410","authenticated-orcid":false,"given":"Linning","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shanghai, China and Shanghai Aritificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0327-4547","authenticated-orcid":false,"given":"Mulin","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Aritificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2445-6112","authenticated-orcid":false,"given":"Yang","family":"Long","sequence":"additional","affiliation":[{"name":"Durham University, Durham, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-9319","authenticated-orcid":false,"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai Aritificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0050-3989","authenticated-orcid":false,"given":"Junting","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai Aritificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_1_2_1","doi-asserted-by":"crossref","unstructured":"Sameer Agarwal Yasutaka Furukawa Noah Snavely Ian Simon Brian Curless Steven\u00a0M Seitz and Richard Szeliski. 2011. Building rome in a day. Commun. ACM 54 10 (2011) 105\u2013112.","DOI":"10.1145\/2001269.2001293"},{"key":"e_1_3_3_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00031"},{"key":"e_1_3_3_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"e_1_3_3_1_5_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Avetisyan Armen","year":"2024","unstructured":"Armen Avetisyan, Christopher Xie, Henry Howard-Jenkins, Tsun-Yi Yang, Samir Aroudj, Suvam Patra, Fuyang Zhang, Duncan Frost, Luke Holland, Campbell Orme, Jakob Engel, Edward Miller, Richard Newcombe, and Vasileios Balntas. 2024. SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00619"},{"key":"e_1_3_3_1_7_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Baruch Gilad","year":"2021","unstructured":"Gilad Baruch, Zhuoyuan Chen, Afshin Dehghan, Tal Dimry, Yuri Feigin, Peter Fu, Thomas Gebauer, Brandon Joffe, Daniel Kurz, Arik Schwartz, and Elad Shulman. 2021. ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1). https:\/\/openreview.net\/forum?id=tjZjv_qh_CE"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"e_1_3_3_1_9_1","unstructured":"Yohann Cabon Naila Murray and Martin Humenberger. 2020. Virtual KITTI 2. arxiv:https:\/\/arXiv.org\/abs\/2001.10773\u00a0[cs.CV]"},{"key":"e_1_3_3_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"e_1_3_3_1_12_1","unstructured":"Xianze Fang Jingnan Gao Zhe Wang Zhuo Chen Xingyu Ren Jiangjing Lyu Qiaomu Ren Zhonglei Yang Xiaokang Yang Yichao Yan et\u00a0al. 2025. Dens3r: A foundation model for 3d geometry prediction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.16290 (2025)."},{"key":"e_1_3_3_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00796"},{"key":"e_1_3_3_1_14_1","doi-asserted-by":"crossref","unstructured":"Andreas Geiger Philip Lenz Christoph Stiller and Raquel Urtasun. 2013. Vision meets robotics: The KITTI dataset. The International Journal of Robotics Research 32 11 (2013) 1231\u20131237.","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_3_1_15_1","doi-asserted-by":"crossref","unstructured":"Klaus Greff Francois Belletti Lucas Beyer Carl Doersch Yilun Du Daniel Duckworth David\u00a0J Fleet Dan Gnanapragasam Florian Golemo Charles Herrmann Thomas Kipf Abhijit Kundu Dmitry Lagun Issam Laradji Hsueh-Ti\u00a0(Derek) Liu Henning Meyer Yishu Miao Derek Nowrouzezahrai Cengiz Oztireli Etienne Pot Noha Radwan Daniel Rebain Sara Sabour Mehdi S.\u00a0M. Sajjadi Matan Sela Vincent Sitzmann Austin Stone Deqing Sun Suhani Vora Ziyu Wang Tianhao Wu Kwang\u00a0Moo Yi Fangcheng Zhong and Andrea Tagliasacchi. 2022. Kubric: a scalable dataset generator. (2022).","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"e_1_3_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"e_1_3_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00499"},{"key":"e_1_3_3_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/861369"},{"key":"e_1_3_3_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00298"},{"key":"e_1_3_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"e_1_3_3_1_21_1","doi-asserted-by":"crossref","unstructured":"Nikita Karaev Iurii Makarov Jianyuan Wang Natalia Neverova Andrea Vedaldi and Christian Rupprecht. 2024. CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. arxiv.","DOI":"10.1109\/ICCV51701.2025.00568"},{"key":"e_1_3_3_1_22_1","doi-asserted-by":"crossref","unstructured":"Nikita Karaev Ignacio Rocco Benjamin Graham Natalia Neverova Andrea Vedaldi and Christian Rupprecht. 2023a. CoTracker: It is Better to Track Together. arxiv.","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"e_1_3_3_1_23_1","doi-asserted-by":"crossref","unstructured":"Nikita Karaev Ignacio Rocco Benjamin Graham Natalia Neverova Andrea Vedaldi and Christian Rupprecht. 2023b. DynamicStereo: Consistent Dynamic Depth from Stereo Videos. CVPR (2023).","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"e_1_3_3_1_24_1","unstructured":"Nikhil Keetha Norman M\u00fcller Johannes Sch\u00f6nberger Lorenzo Porzi Yuchen Zhang Tobias Fischer Arno Knapitsch Duncan Zauss Ethan Weber Nelson Antunes et\u00a0al. 2025. Mapanything: Universal feed-forward metric 3d reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.13414 (2025)."},{"key":"e_1_3_3_1_25_1","doi-asserted-by":"crossref","unstructured":"Skanda Koppula Ignacio Rocco Yi Yang Joe Heyward Jo\u00e3o Carreira Andrew Zisserman Gabriel Brostow and Carl Doersch. 2024. TAPVid-3D: A Benchmark for Tracking Any Point in 3D. arxiv:https:\/\/arXiv.org\/abs\/2407.05921\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2407.05921","DOI":"10.52202\/079017-2611"},{"key":"e_1_3_3_1_26_1","doi-asserted-by":"crossref","unstructured":"Vincent Leroy Yohann Cabon and Jerome Revaud. 2024. Grounding Image Matching in 3D with MASt3R.","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"e_1_3_3_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"e_1_3_3_1_28_1","unstructured":"Zhen Li Chuanhao Li Xiaofeng Mao Shaoheng Lin Ming Li Shitian Zhao Zhaopan Xu Xinyue Li Yukang Feng Jianwen Sun Zizhen Li Fanrui Zhang Jiaxin Ai Zhixiang Wang Yuwei Wu Tong He Jiangmiao Pang Yu Qiao Yunde Jia and Kaipeng Zhang. 2025a. Sekai: A Video Dataset towards World Exploration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.15675 (2025)."},{"key":"e_1_3_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"e_1_3_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"e_1_3_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"e_1_3_3_1_32_1","doi-asserted-by":"crossref","unstructured":"David\u00a0G Lowe. 2004. Distinctive image features from scale-invariant keypoints. International journal of computer vision 60 2 (2004) 91\u2013110.","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_3_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"e_1_3_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01556"},{"key":"e_1_3_3_1_35_1","volume-title":"ECCV","author":"Derek\u00a0Hoiem Pushmeet\u00a0Kohli Nathan\u00a0Silberman,","year":"2012","unstructured":"Pushmeet\u00a0Kohli Nathan\u00a0Silberman, Derek\u00a0Hoiem and Rob Fergus. 2012. Indoor Segmentation and Support Inference from RGBD Images. In ECCV."},{"key":"e_1_3_3_1_36_1","unstructured":"Tuan\u00a0Duc Ngo Ashkan Mirzaei Guocheng Qian Hanwen Liang Chuang Gan Evangelos Kalogerakis Peter Wonka and Chaoyang Wang. 2025. DELTAv2: Accelerating Dense 3D Tracking. arxiv:https:\/\/arXiv.org\/abs\/2508.01170\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2508.01170"},{"key":"e_1_3_3_1_37_1","unstructured":"Tuan\u00a0Duc Ngo Peiye Zhuang Chuang Gan Evangelos Kalogerakis Sergey Tulyakov Hsin-Ying Lee and Chaoyang Wang. 2024. DELTA: Dense Efficient Long-range 3D Tracking for Any video. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.24211 (2024)."},{"key":"e_1_3_3_1_38_1","doi-asserted-by":"crossref","unstructured":"Emanuele Palazzolo Jens Behley Philipp Lottes Philippe Gigu\u00e8re and Cyrill Stachniss. 2019. ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals. arxiv:https:\/\/arXiv.org\/abs\/1905.02082\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/1905.02082","DOI":"10.1109\/IROS40897.2019.8967590"},{"key":"e_1_3_3_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"e_1_3_3_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00013"},{"key":"e_1_3_3_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"e_1_3_3_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"e_1_3_3_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_3_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"e_1_3_3_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.377"},{"key":"e_1_3_3_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"e_1_3_3_1_47_1","doi-asserted-by":"crossref","unstructured":"Pei Sun Henrik Kretzschmar Xerxes Dotiwalla Aurelien Chouard Vijaysai Patnaik Paul Tsui James Guo Yin Zhou Yuning Chai Benjamin Caine Vijay Vasudevan Wei Han Jiquan Ngiam Hang Zhao Aleksei Timofeev Scott Ettinger Maxim Krivokon Amy Gao Aditya Joshi Sheng Zhao Shuyang Cheng Yu Zhang Jonathon Shlens Zhifeng Chen and Dragomir Anguelov. 2020. Scalability in Perception for Autonomous Driving: Waymo Open Dataset. arxiv:https:\/\/arXiv.org\/abs\/1912.04838\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1912.04838","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"e_1_3_3_1_48_1","doi-asserted-by":"crossref","unstructured":"Zhenggang Tang Yuchen Fan Dilin Wang Hongyu Xu Rakesh Ranjan Alexander Schwing and Zhicheng Yan. 2024. MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.06974 (2024).","DOI":"10.1109\/CVPR52734.2025.00498"},{"key":"e_1_3_3_1_49_1","unstructured":"Aether Team Haoyi Zhu Yifan Wang Jianjun Zhou Wenzheng Chang Yang Zhou Zizun Li Junyi Chen Chunhua Shen Jiangmiao Pang and Tong He. 2025. Aether: Geometric-Aware Unified World Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.18945 (2025)."},{"key":"e_1_3_3_1_50_1","unstructured":"Zachary Teed and Jia Deng. 2021. Droid-slam: Deep visual slam for monocular stereo and rgb-d cameras. Advances in neural information processing systems 34 (2021) 16558\u201316569."},{"key":"e_1_3_3_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/646271.685629"},{"key":"e_1_3_3_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"e_1_3_3_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"e_1_3_3_1_54_1","unstructured":"Kaixuan Wang and Shaojie Shen. 2019. Flow-Motion and Depth Network for Monocular Stereo and Beyond. arxiv:https:\/\/arXiv.org\/abs\/1909.05452\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1909.05452"},{"key":"e_1_3_3_1_55_1","doi-asserted-by":"crossref","unstructured":"Qianqian Wang Yen-Yu Chang Ruojin Cai Zhengqi Li Bharath Hariharan Aleksander Holynski and Noah Snavely. 2023a. Tracking Everything Everywhere All at Once. ICCV (2023).","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"e_1_3_3_1_56_1","doi-asserted-by":"crossref","unstructured":"Qianqian Wang Yifei Zhang Aleksander Holynski Alexei\u00a0A Efros and Angjoo Kanazawa. 2025d. Continuous 3D Perception Model with Persistent State. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12387 (2025).","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"e_1_3_3_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"e_1_3_3_1_58_1","unstructured":"Ruicheng Wang Sicheng Xu Yue Dong Yu Deng Jianfeng Xiang Zelong Lv Guangzhong Sun Xin Tong and Jiaolong Yang. 2025c. MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details. arxiv:https:\/\/arXiv.org\/abs\/2507.02546\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2507.02546"},{"key":"e_1_3_3_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"e_1_3_3_1_60_1","doi-asserted-by":"crossref","unstructured":"Wenshan Wang Delong Zhu Xiangwei Wang Yaoyu Hu Yuheng Qiu Chen Wang Yafei Hu Ashish Kapoor and Sebastian Scherer. 2020. TartanAir: A Dataset to Push the Limits of Visual SLAM. (2020).","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"e_1_3_3_1_61_1","unstructured":"Yifan Wang Jianjun Zhou Haoyi Zhu Wenzheng Chang Yang Zhou Zizun Li Junyi Chen Jiangmiao Pang Chunhua Shen and Tong He. 2025e. \u03c03: Permutation-Equivariant Visual Geometry Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.13347 (2025)."},{"key":"e_1_3_3_1_62_1","unstructured":"Hongchi Xia Yang Fu Sifei Liu and Xiaolong Wang. 2024. RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos. arxiv:https:\/\/arXiv.org\/abs\/2401.12592\u00a0[cs.CV]"},{"key":"e_1_3_3_1_63_1","volume-title":"ICCV","author":"Xiao Yuxi","year":"2025","unstructured":"Yuxi Xiao, Jianyuan Wang, Nan Xue, Nikita Karaev, Iurii Makarov, Bingyi Kang, Xin Zhu, Hujun Bao, Yujun Shen, and Xiaowei Zhou. 2025. SpatialTrackerV2: 3D Point Tracking Made Easy. In ICCV."},{"key":"e_1_3_3_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"e_1_3_3_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"e_1_3_3_1_66_1","doi-asserted-by":"crossref","unstructured":"Yao Yao Zixin Luo Shiwei Li Jingyang Zhang Yufan Ren Lei Zhou Tian Fang and Long Quan. 2020. BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks. Computer Vision and Pattern Recognition (CVPR) (2020).","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"e_1_3_3_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"e_1_3_3_1_68_1","unstructured":"Bowei Zhang Lei Ke Adam\u00a0W Harley and Katerina Fragkiadaki. 2025a. TAPIP3D: Tracking Any Point in Persistent 3D Geometry. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.14717 (2025)."},{"key":"e_1_3_3_1_69_1","unstructured":"Chuhan Zhang Guillaume\u00a0Le Moing Skanda Koppula Ignacio Rocco Liliane Momeni Junyu Xie Shuyang Sun Rahul Sukthankar Jo\u00eblle\u00a0K Barral Raia Hadsell et\u00a0al. 2025b. Efficiently reconstructing dynamic scenes one d4rt at a time. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.08924 (2025)."},{"key":"e_1_3_3_1_70_1","unstructured":"Junyi Zhang Charles Herrmann Junhwa Hur Varun Jampani Trevor Darrell Forrester Cole Deqing Sun and Ming-Hsuan Yang. 2024. MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion. arXiv preprint arxiv:https:\/\/arXiv.org\/abs\/2410.03825 (2024)."},{"key":"e_1_3_3_1_71_1","doi-asserted-by":"crossref","unstructured":"Shangzhan Zhang Jianyuan Wang Yinghao Xu Nan Xue Christian Rupprecht Xiaowei Zhou Yujun Shen and Gordon Wetzstein. 2025c. FLARE: Feed-forward Geometry Appearance and Camera Estimation from Uncalibrated Sparse Views. arxiv:https:\/\/arXiv.org\/abs\/2502.12138\u00a0[cs.CV]","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"e_1_3_3_1_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"e_1_3_3_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"e_1_3_3_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"e_1_3_3_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"e_1_3_3_1_76_1","unstructured":"Yang Zhou Yifan Wang Jianjun Zhou Wenzheng Chang Haoyu Guo Zizun Li Kaijing Ma Xinyue Li Yating Wang Haoyi Zhu Mingyu Liu Dingning Liu Jiange Yang Zhoujie Fu Junyi Chen Chunhua Shen Jiangmiao Pang Kaipeng Zhang and Tong He. 2025. OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.12201 (2025)."}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","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":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:18:06Z","timestamp":1784225886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":75,"alternative-id":["10.1145\/3799902.3811184","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811184","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}