{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:07:18Z","timestamp":1789024038448,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372109","type":"print"},{"value":"9783032372116","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37211-6_7","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:41:41Z","timestamp":1789022501000},"page":"112-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5282-8977","authenticated-orcid":false,"given":"Si-Yu","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9958-0994","authenticated-orcid":false,"given":"Po-Ting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1607-6319","authenticated-orcid":false,"given":"Hui-Che","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4481-1633","authenticated-orcid":false,"given":"Sin-Ye","family":"Jhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4662-7875","authenticated-orcid":false,"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6852-8862","authenticated-orcid":false,"given":"Yung-Yao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Azinovi\u0107, D., Martin-Brualla, R., Goldman, D.B., Nie\u00dfner, M., Thies, J.: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6290\u20136301 (2022). Neural RGB-D Surface Reconstruction","DOI":"10.1109\/CVPR52688.2022.00619"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Cabon, Y., et al.: MUSt3R: multi-view network for stereo 3D reconstruction. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.00106"},{"issue":"6","key":"7_CR3","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., Rodr\u00edguez, J.J.G., Montiel, J.M.M., Tard\u00f3s, J.D.: ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap SLAM. IEEE Trans. Rob. 37(6), 1874\u20131890 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"7_CR4","unstructured":"Chen, X., Chen, Y., Xiu, Y., Geiger, A., Chen, A.: TTT3R: 3D Reconstruction as Test-Time Training. arXiv preprint:2509.26645 (2025)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, S., Ko, B., Kim, E., Kil, J., Kim, H.J.: Representation Shift: Unifying Token Compression with FlashAttention. In: IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.01902"},{"key":"7_CR6","unstructured":"Dao, T.: FlashAttention-2: faster attention with better parallelism and work partitioning. In: International Conference on Learning Representations (2024)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D.Y., Ermon, S., Rudra, A., R\u00e9, C.: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. In: Advances in Neural Information Processing Systems (2022)","DOI":"10.52202\/068431-1189"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Feng, Y., Lv, J., Cao, Y., Xie, X., Zhou, S.K.: AdaKV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference (2024). arXiv preprint\u202f:2407.11550","DOI":"10.52202\/085713-3773"},{"issue":"8","key":"7_CR10","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TPAMI.2009.161","volume":"32","author":"Y Furukawa","year":"2010","unstructured":"Furukawa, Y., Ponce, J.: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell. 32(8), 1362\u20131376 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets Robotics: The KITTI Dataset. Int. J. Robot. Res. (2013)","DOI":"10.1177\/0278364913491297"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3D with MASt3R. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Pollefeys, M.: LightGlue: local feature matching at light speed. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Lipson, L., Teed, Z., Deng, J.: Deep patch visual SLAM. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72627-9_24"},{"key":"7_CR16","unstructured":"Mahdi, S., Ayar, F., Javanmardi, E., Tsukada, M., Javanmardi, M.: Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers. arXiv preprint: 2509.17650 (2025)"},{"issue":"5","key":"7_CR17","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tard\u00f3s, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"issue":"5","key":"7_CR18","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R., Tard\u00f3s, J.D.: ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Trans. Rob. 33(5), 1255\u20131262 (2017)","journal-title":"IEEE Trans. Rob."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Murai, R., Orb, E., Nicholson, L., Masuda, K., Tateno, K., Tombari, F.: MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (2024). arXiv preprint\u202f:2412.12392","DOI":"10.1109\/CVPR52734.2025.01556"},{"key":"7_CR20","unstructured":"Oquab, M., et al.: DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research (2024)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Palazzolo, E., Behley, J., Lottes, P., Giguere, P., Stachniss, C.: ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (2019)","DOI":"10.1109\/IROS40897.2019.8967590"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Pan, L., Barath, D., Pollefeys, M., Sch\u00f6nberger, J.L.: Global Structure-from-Motion Revisited. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Pollefeys, M., Frahm, J.M.: Pixelwise view selection for unstructured multi-view stereo. In: European Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Schops, T., et al.: A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.272"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2013)","DOI":"10.1109\/CVPR.2013.377"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Tang, Z., Fan, Y., Wang, D., Xu, H., Ranjan, R., Schwing, A., Yan, Z.: MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views in 2 Seconds. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.00498"},{"key":"7_CR29","unstructured":"Teed, Z., Deng, J.: DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. In: Advances in Neural Information Processing Systems (2021)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Teed, Z., Lipson, L., Deng, J.: Deep Patch Visual Odometry. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/075280-1696"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. In: IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M.: PatchmatchNet: learned multi-view patchmatch stereo. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: Spann3R: 3D reconstruction with spatial memory. In: International Conference on 3D Vision (3DV) (2025)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Wang, J., Karaev, N., Rupprecht, C., Novotny, D.: VGGSfM: visual geometry grounded deep structure from motion. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D Perception Model with Persistent State (2025). arXiv preprint\u202f:2501.12387","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: geometric 3D vision made easy. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zheng, W., Zhou, J., Lu, J.: Point3R: streaming 3D Reconstruction with Explicit Spatial Pointer Memory (2025). arXiv preprint\u202f:2507.02863","DOI":"10.52202\/085713-2344"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: Depth Inference for Unstructured Multi-View Stereo. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"7_CR41","unstructured":"Yuan, S., et al.: InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams. arXiv preprint :2601.02281 (2026)"},{"key":"7_CR42","unstructured":"Zhang, J., Herrmann, C., Hur, J., Jampani, V., Sun, D., Yang, M.H.: MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (2024). arXiv preprint\u202f:2410.03825"},{"key":"7_CR43","unstructured":"Zhuo, D., Zheng, W., Guo, J., Wu, Y., Zhou, J., Lu, J.: Streaming 4D Visual Geometry Transformer, pp. 2507\u201311539 (2025). arXiv preprint"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37211-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:41:58Z","timestamp":1789022518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37211-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372109","9783032372116"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37211-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}