{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:10:48Z","timestamp":1789042248806,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370914","type":"print"},{"value":"9783032370921","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\/978-3-032-37092-1_20","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:25:25Z","timestamp":1789039525000},"page":"353-371","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FoundationGeo: Learning Spatial Pixel-Wise Fields for\u00a0Monocular Metric Geometry"],"prefix":"10.1007","author":[{"given":"Muxin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhe","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiehong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoshuai","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"20_CR1","unstructured":"Baruch, G., et al.: 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) (2021)"},{"key":"20_CR2","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)"},{"key":"20_CR3","unstructured":"Bochkovskii, A., et al.: Depth pro: Sharp monocular metric depth in less than a second. In: International Conference on Learning Representations (2025)"},{"key":"20_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/978-3-642-33783-3_44","volume-title":"Computer Vision \u2013 ECCV 2012","author":"DJ Butler","year":"2012","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A Naturalistic Open Source Movie for Optical Flow Evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611\u2013625. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_44"},{"key":"20_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"20_CR6","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in neural information processing systems, p. 27 (2014)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Fonder, M., Van Droogenbroeck, M.: Mid-air: A multi-modal dataset for extremely low altitude drone flights. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00081"},{"key":"20_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130038","volume":"637","author":"JL G\u00f3mez","year":"2025","unstructured":"G\u00f3mez, J.L., et al.: All for one, and one for all: Urbansyn dataset, the third musketeer of synthetic driving scenes. Neurocomputing 637, 130038 (2025)","journal-title":"Neurocomputing"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3d packing for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2485\u20132494 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"issue":"12","key":"20_CR10","doi-asserted-by":"publisher","first-page":"10579","DOI":"10.1109\/TPAMI.2024.3444912","volume":"46","author":"M Hu","year":"2024","unstructured":"Hu, M., et al.: Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 10579\u201310596 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: Deepmvs: Learning multi-view stereopsis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2821\u20132830 (2018)","DOI":"10.1109\/CVPR.2018.00298"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Jung, H., et al.: On the importance of accurate geometry data for dense 3d vision tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 780\u2013791 (2023)","DOI":"10.1109\/CVPR52729.2023.00082"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: Dynamicstereo: Consistent dynamic depth from stereo videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13229\u201313239 (2023)","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Ke, B., et al.: Marigold: Affordable adaptation of diffusion-based image generators for image analysis. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3591076"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Koch, T., Liebel, L., Fraundorfer, F., Korner, M.: Evaluation of cnn-based single-image depth estimation methods. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11015-4_25"},{"key":"20_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102877","volume":"191","author":"T Koch","year":"2020","unstructured":"Koch, T., Liebel, L., K\u00f6rner, M., Fraundorfer, F.: Comparison of monocular depth estimation methods using geometrically relevant metrics on the ibims-1 dataset. Comput. Vis. Image Underst. 191, 102877 (2020)","journal-title":"Comput. Vis. Image Underst."},{"key":"20_CR17","doi-asserted-by":"publisher","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3d with mast3r. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 71\u201391. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73220-1_5","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Matrixcity: A large-scale city dataset for city-scale neural rendering and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3205\u20133215 (2023)","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"20_CR19","unstructured":"Lin, H., et al.: Depth anything 3: Recovering the visual space from any views. In: International Conference on Learning Representations (2026)"},{"key":"20_CR20","unstructured":"Lyu, X., et al.: Stabilizing streaming video geometry via dynamic feature normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7577\u20137587 (2026)"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Mehl, L., Schmalfuss, J., Jahedi, A., Nalivayko, Y., Bruhn, A.: Spring: A high-resolution high-detail dataset and benchmark for scene flow, optical flow and stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4981\u20134991 (2023)","DOI":"10.1109\/CVPR52729.2023.00482"},{"issue":"6","key":"20_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355089.3356528","volume":"38","author":"S Niklaus","year":"2019","unstructured":"Niklaus, S., Mai, L., Yang, J., Liu, F.: 3d ken burns effect from a single image. ACM Trans. Graph. (ToG) 38(6), 1\u201315 (2019)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: Unidepthv2: Universal monocular metric depth estimation made simpler. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3628473"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: Unidepth: Universal monocular metric depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10106\u201310116 (2024)","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Liu, Z., Urtasun, R., Jia, J.: Geonet: Geometric neural network for joint depth and surface normal estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 283\u2013291 (2018)","DOI":"10.1109\/CVPR.2018.00037"},{"issue":"2","key":"20_CR26","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1109\/TPAMI.2020.3020800","volume":"44","author":"X Qi","year":"2020","unstructured":"Qi, X., Liu, Z., Liao, R., Torr, P.H., Urtasun, R., Jia, J.: Geonet++: Iterative geometric neural network with edge-aware refinement for joint depth and surface normal estimation. IEEE Trans. Pattern Anal. Mach. Intell. 44(2), 969\u2013984 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: A photorealistic synthetic dataset for holistic indoor scene understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10912\u201310922 (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"20_CR29","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3d: Depth perception from a single still image. In: AAAI, Vol. 3, pp. 1571\u20131576 (2008)"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Schops, T., Sattler, T., Pollefeys, M.: Bad slam: Bundle adjusted direct rgb-d slam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 134\u2013144 (2019)","DOI":"10.1109\/CVPR.2019.00022"},{"key":"20_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor Segmentation and Support Inference from RGBD Images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"20_CR32","unstructured":"Sim\u00e9oni, O., et\u00a0al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant cnns. In: 2017 International Conference on 3D Vision (3DV), pp. 11\u201320. IEEE (2017)","DOI":"10.1109\/3DV.2017.00012"},{"key":"20_CR35","unstructured":"Vasiljevic, I., et al.: Diode: A dense indoor and outdoor depth dataset. arXiv preprint arXiv:1908.00463 (2019)"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: Vggt: Visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zheng, S., Yan, Q., Deng, F., Zhao, K., Chu, X.: Irs: A large naturalistic indoor robotics stereo dataset to train deep models for disparity and surface normal estimation. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428423"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Moge: Unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5261\u20135271. (2025)","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"20_CR39","first-page":"35928","volume":"38","author":"R Wang","year":"2025","unstructured":"Wang, R., et al.: Moge-2: Accurate monocular geometry with metric scale and sharp details. Adv. Neural. Inf. Process. Syst. 38, 35928\u201335959 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Wet al.: Tartanair: A dataset to push the limits of visual slam. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4909\u20134916. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Wen, B., Trepte, M., Aribido, J., Kautz, J., Gallo, O., Birchfield, S.: Foundationstereo: Zero-shot stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5249\u20135260 (2025)","DOI":"10.1109\/CVPR52734.2025.00495"},{"key":"20_CR42","unstructured":"Wilson, B., et al.: Argoverse 2: Next generation datasets for self-driving perception and forecasting. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021) (2021)"},{"key":"20_CR43","first-page":"174731","volume":"38","author":"G Xu","year":"2025","unstructured":"Xu, G., et al.: Pixel-perfect depth with semantics-prompted diffusion transformers. Adv. Neural. Inf. Process. Syst. 38, 174731\u2013174755 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: Unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"20_CR45","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth anything v2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Blendedmvs: A large-scale dataset for generalized multi-view stereo networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1790\u20131799 (2020)","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Yin, W.,et al.: Metric3d: Towards zero-shot metric 3d prediction from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9043\u20139053 (2023)","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: Disentangling task transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3712\u20133722 (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"20_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-030-58545-7_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Zheng","year":"2020","unstructured":"Zheng, J., Zhang, J., Li, J., Tang, R., Gao, S., Zhou, Z.: Structured3D: A Large Photo-Realistic Dataset for Structured 3D Modeling. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 519\u2013535. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_30"}],"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\/978-3-032-37092-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:25:40Z","timestamp":1789039540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37092-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370914","9783032370921"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37092-1_20","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"}}]}}