{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:07:27Z","timestamp":1789124847776,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376015","type":"print"},{"value":"9783032376022","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\/978-3-032-37602-2_32","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:21:31Z","timestamp":1789122091000},"page":"564-582","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OmniPoint: Universal Monocular Metric Pointcloud from\u00a0Any Camera"],"prefix":"10.1007","author":[{"given":"Botao","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhijit","family":"Kundu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"32_CR1","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D-3D-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)"},{"key":"32_CR2","unstructured":"Baruch, G., et al.: ARKitScenes: a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data (2021). arXiv preprint arXiv:2111.08897"},{"key":"32_CR3","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: ZoeDepth: zero-shot transfer by combining relative and metric depth (2023). arXiv preprint arXiv:2302.12288"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Black, M.J., Patel, P., Tesch, J., Yang, J.: Bedlam: a synthetic dataset of bodies exhibiting detailed lifelike animated motion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"32_CR5","unstructured":"Bochkovskii, A., et al.: Depth pro: sharp monocular metric depth in less than a second, In. ICLR (2024)"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"32_CR7","unstructured":"Cabon, Y., Murray, N., Humenberger, M.: Virtual kitti 2 (2020). arXiv preprint arXiv:2001.10773"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., et al.: Panda: towards panoramic depth anything with unlabeled panoramas and mobius spatial augmentation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00100"},{"key":"32_CR9","unstructured":"Cao, Z., Zhu, J., Zhang, W., Wang, L.: Any360d: towards 360 depth anything with unlabeled 360 data and m\u00f6bius spatial augmentation. arxiv preprint arXiv:2406.13378v1 (2024)"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments, (2017). arXiv preprint arXiv:1709.06158","DOI":"10.1109\/3DV.2017.00081"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Chen, H., Hou, Y., Qu, C., Testini, I., Hong, X., Jiao, J.: 360+ x: a panoptic multi-modal scene understanding dataset. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01833"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Downs, L., et al.: Google scanned objects: a high-quality dataset of 3d scanned household items. In: ICRA (2022)","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"32_CR13","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":"32_CR14","doi-asserted-by":"crossref","unstructured":"Feng, H., Wang, W., Deng, J., Zhou, W., Li, L., Li, H.: SimFIR: a simple framework for fisheye image rectification with self-supervised representation learning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01141"},{"issue":"11","key":"32_CR15","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: The kitti dataset. The international journal of robotics research 32(11), 1231\u20131237 (2013)","journal-title":"The international journal of robotics research"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Guo, Y., Garg, S., Miangoleh, S.M.H., Huang, X., Ren, L.: Depth any camera: zero-shot metric depth estimation from any camera. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02514"},{"key":"32_CR17","doi-asserted-by":"crossref","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)","DOI":"10.1016\/j.neucom.2025.130038"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Hu, M., et al.: Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. IEEE TPAMI 46(12), 10579\u201310596 (2024)","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: Deepmvs: learning multi-view stereopsis. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00298"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Jung, H., et al.: On the importance of accurate geometry data for dense 3D vision tasks. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00082"},{"key":"32_CR21","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Koch, T., Liebel, L., Fraundorfer, F., Korner, M.: Evaluation of CNN-based single-image depth estimation methods. In: ECCV Workshops (2018)","DOI":"10.1007\/978-3-030-11015-4_25"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Kornilova, A., et al.: Smartportraits: depth powered handheld smartphone dataset of human portraits for state estimation, reconstruction and synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02063"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Le, H.A., Mensink, T., Das, P., Karaoglu, S., Gevers, T.: Eden: multimodal synthetic dataset of enclosed garden scenes. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00162"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Lee, J., Cho, G., Park, J., Kim, K., Lee, S., Kim, J.H., Jeong, S.G., Joo, K.: Slabins: fisheye depth estimation using slanted bins on road environments. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00805"},{"key":"32_CR27","unstructured":"Li, H., et al.: Da2: depth anything in any direction. arXiv preprint arXiv:2509.26618 (2025)"},{"issue":"3","key":"32_CR28","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1109\/TPAMI.2022.3179507","volume":"45","author":"Y Liao","year":"2022","unstructured":"Liao, Y., Xie, J., Geiger, A.: Kitti-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. IEEE TPAMI 45(3), 3292\u20133310 (2022)","journal-title":"IEEE TPAMI"},{"key":"32_CR29","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint arXiv:2511.10647 (2025)"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Lin, H., et al.: Prompting depth anything for 4k resolution accurate metric depth estimation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01591"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: HOI4D: a 4D egocentric dataset for category-level human-object interaction. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"32_CR32","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Fergus, P.K., R.: Indoor segmentation and support inference from RGBD images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"issue":"6","key":"32_CR34","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 TOG 38(6), 1\u201315 (2019)","journal-title":"ACM TOG"},{"key":"32_CR35","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2023). arXiv preprint arXiv:2304.07193"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., Sakaridis, C., Segu, M., Yang, Y.H., Li, S., Abbeloos, W., Van Gool, L.: UniK3D: Universal camera monocular 3D estimation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00104"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., Sakaridis, C., Yang, Y.H., Segu, M., Li, S., Abbeloos, W., Van Gool, L.: Unidepthv2: universal monocular metric depth estimation made simpler (2025). arXiv preprint arXiv:2502.20110","DOI":"10.1109\/TPAMI.2025.3628473"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., Yang, Y.H., Sakaridis, C., Segu, M., Li, S., Van Gool, L., Yu, F.: Unidepth: Universal monocular metric depth estimation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"32_CR40","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE TPAMI 44(3), 1623\u20131637 (2020)","journal-title":"IEEE TPAMI"},{"key":"32_CR41","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"32_CR42","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"32_CR43","doi-asserted-by":"crossref","unstructured":"Schops, T., Sattler, T., Pollefeys, M.: Bad slam: Bundle adjusted direct RGB-D slam. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00022"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"32_CR45","doi-asserted-by":"crossref","unstructured":"Tang, J., Tian, F.P., An, B., Li, J., Tan, P.: Bilateral propagation network for depth completion. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00932"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Tosi, F., Liao, Y., Schmitt, C., Geiger, A.: SMD-Nets: stereo mixture density networks. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00883"},{"key":"32_CR47","unstructured":"Vasiljevic, I., et al.: Diode: a dense indoor and outdoor depth dataset (2019). arXiv preprint arXiv:1908.00463"},{"key":"32_CR48","doi-asserted-by":"crossref","unstructured":"Wang, F.E., et al.: Self-supervised learning of depth and camera motion from 360 videos. In: ACCV (2018)","DOI":"10.1007\/978-3-030-20873-8_4"},{"key":"32_CR49","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"32_CR50","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 (2019). arXiv preprint arXiv:1912.09678"},{"key":"32_CR51","doi-asserted-by":"crossref","unstructured":"Wang, R., Xu, S., Dai, C., Xiang, J., Deng, Y., Tong, X., Yang, J.: MoGe: unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"32_CR52","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: MoGe-2: accurate monocular geometry with metric scale and sharp details. NeurIPS (2025)","DOI":"10.52202\/085713-1207"},{"key":"32_CR53","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: Geometric 3D vision made easy. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"32_CR54","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Tartanair: a dataset to push the limits of visual slam. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"32_CR55","unstructured":"Wang, Z., et al.: Depth anything with any prior. arXiv preprint arXiv:2505.10565 (2025)"},{"key":"32_CR56","unstructured":"Wrenninge, M., Unger, J.: Synscapes: a photorealistic synthetic dataset for street scene parsing, (2018). arXiv preprint arXiv:1810.08705"},{"key":"32_CR57","doi-asserted-by":"crossref","unstructured":"Wu, T., et\u00a0al.: Omniobject3d: large-vocabulary 3d object dataset for realistic perception, reconstruction and generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"32_CR58","doi-asserted-by":"crossref","unstructured":"Xia, H., Fu, Y., Liu, S., Wang, X.: RGBD objects in the wild: scaling real-world 3D object learning from RGB-D videos. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"32_CR59","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR60","doi-asserted-by":"crossref","unstructured":"Xie, S., Wang, D., Liu, Y.H.: Omnividar: omnidirectional depth estimation from multi-fisheye images. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02062"},{"key":"32_CR61","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: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"32_CR62","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., Zhao, H.: Depth anything v2. In: NeurIPS (2024)","DOI":"10.52202\/079017-0688"},{"key":"32_CR63","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Blendedmvs: a large-scale dataset for generalized multi-view stereo networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"32_CR64","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: Scannet++: A high-fidelity dataset of 3D indoor scenes. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"32_CR65","doi-asserted-by":"crossref","unstructured":"Zheng, J., Zhang, J., Li, J., Tang, R., Gao, S., Zhou, Z.: Structured3d: a large photo-realistic dataset for structured 3d modeling. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"32_CR66","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Harley, A.W., Shen, B., Wetzstein, G., Guibas, L.J.: Pointodyssey: a large-scale synthetic dataset for long-term point tracking. In. ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"32_CR67","unstructured":"Zhou, Y., et\u00a0al.: Omniworld: a multi-domain and multi-modal dataset for 4d world modeling. arXiv preprint arXiv:2509.12201 (2025)"},{"key":"32_CR68","doi-asserted-by":"crossref","unstructured":"Zuo, Y., Deng, J.: OGNI-DC: robust depth completion with optimization-guided neural iterations. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72646-0_5"}],"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\/978-3-032-37602-2_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:21:56Z","timestamp":1789122116000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37602-2_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376015","9783032376022"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37602-2_32","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":"12 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"}}]}}