{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:45:24Z","timestamp":1777653924585,"version":"3.51.4"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72970-6_20","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:52:04Z","timestamp":1732272724000},"page":"349-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Geospecific View Generation Geometry-Context Aware High-Resolution Ground View Inference from\u00a0Satellite Views"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0421-7349","authenticated-orcid":false,"given":"Ningli","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5896-1379","authenticated-orcid":false,"given":"Rongjun","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Cai, S., Guo, Y., Khan, S., Hu, J., Wen, G.: Ground-to-aerial image geo-localization with a hard exemplar reweighting triplet loss. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8391\u20138400 (2019)","DOI":"10.1109\/ICCV.2019.00848"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Castaldo, F., Zamir, A., Angst, R., Palmieri, F., Savarese, S.: Semantic cross-view matching. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 9\u201317 (2015)","DOI":"10.1109\/ICCVW.2015.137"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Chan, C., Durand, F., Isola, P.: Learning to generate line drawings that convey geometry and semantics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7915\u20137925 (2022)","DOI":"10.1109\/CVPR52688.2022.00776"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: Stargan: unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789\u20138797 (2018)","DOI":"10.1109\/CVPR.2018.00916"},{"key":"20_CR5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.5194\/isprsannals-II-3-49-2014","volume":"2","author":"C De Franchis","year":"2014","unstructured":"De Franchis, C., Meinhardt-Llopis, E., Michel, J., Morel, J.M., Facciolo, G.: An automatic and modular stereo pipeline for pushbroom images. ISPRS Ann. Photogrammetry Remote Sens. Spatial Inf. Sci. 2, 49\u201356 (2014)","journal-title":"ISPRS Ann. Photogrammetry Remote Sens. Spatial Inf. Sci."},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12873\u201312883, June 2021","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"20_CR7","unstructured":"Fu, S., Tamir, N., Sundaram, S., Chai, L., Zhang, R., Dekel, T., Isola, P.: Dreamsim: learning new dimensions of human visual similarity using synthetic data. arXiv preprint arXiv:2306.09344 (2023)"},{"key":"20_CR8","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"2","key":"20_CR9","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2007","unstructured":"Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 328\u2013341 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR10","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR11","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Hu, S., Feng, M., Nguyen, R.M.H., Lee, G.H.: Cvm-net: cross-view matching network for image-based ground-to-aerial geo-localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00758"},{"issue":"1","key":"20_CR13","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1080\/15481603.2022.2060595","volume":"59","author":"D Huang","year":"2022","unstructured":"Huang, D., Tang, Y., Qin, R.: An evaluation of planetscope images for 3d reconstruction and change detection-experimental validations with case studies. GISci. Remote Sens. 59(1), 744\u2013761 (2022)","journal-title":"GISci. Remote Sens."},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M.T., Hassani, A., Orlov, N., Shi, H.: Oneformer: one transformer to rule universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2989\u20132998 (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Lentsch, T., Xia, Z., Caesar, H., Kooij, J.F.: Slicematch: Geometry-guided aggregation for cross-view pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17225\u201317234 (2023)","DOI":"10.1109\/CVPR52729.2023.01652"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Leotta, M.J., et al.: Urban semantic 3d reconstruction from multiview satellite imagery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2019","DOI":"10.1109\/CVPRW.2019.00186"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, Z., Cui, Z., Pollefeys, M., Oswald, M.R.: Sat2scene: 3d urban scene generation from satellite images with diffusion. arXiv preprint arXiv:2401.10786 (2024)","DOI":"10.1109\/CVPR52733.2024.00682"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, Z., Cui, Z., Qin, R., Pollefeys, M., Oswald, M.R.: Sat2vid: street-view panoramic video synthesis from a single satellite image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12436\u201312445 (2021)","DOI":"10.1109\/ICCV48922.2021.01221"},{"key":"20_CR20","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1109\/JSTARS.2020.3035274","volume":"14","author":"Y Lian","year":"2021","unstructured":"Lian, Y., et al.: Large-scale semantic 3-d reconstruction: outcome of the 2019 IEEE GRSS data fusion contest-part b. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 14, 1158\u20131170 (2021). https:\/\/doi.org\/10.1109\/JSTARS.2020.3035274","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Belongie, S., Hays, J.: Cross-view image geolocalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2013)","DOI":"10.1109\/CVPR.2013.120"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, Z., Cui, Z., Oswald, M.R., Pollefeys, M., Qin, R.: Geometry-aware satellite-to-ground image synthesis for urban areas. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 859\u2013867 (2020)","DOI":"10.1109\/CVPR42600.2020.00094"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"20_CR24","unstructured":"OpenStreetMap contributors: planet dump retrieved from https:\/\/planet.osm.org, https:\/\/www.openstreetmap.org (2017)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Qian, M., Xiong, J., Xia, G.S., Xue, N.: Sat2density: faithful density learning from satellite-ground image pairs. arXiv preprint arXiv:2303.14672 (2023)","DOI":"10.1109\/ICCV51070.2023.00341"},{"key":"20_CR27","doi-asserted-by":"publisher","first-page":"77","DOI":"10.5194\/isprs-annals-III-1-77-2016","volume":"3","author":"R Qin","year":"2016","unstructured":"Qin, R.: RPC stereo processor (RSP)-a software package for digital surface model and orthophoto generation from satellite stereo imagery. ISPRS Ann. Photogrammetry Remote Sens. Spatial Inf. Sci. 3, 77\u201382 (2016)","journal-title":"ISPRS Ann. Photogrammetry Remote Sens. Spatial Inf. Sci."},{"key":"20_CR28","unstructured":"Reed, S.E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Regmi, K., Borji, A.: Cross-view image synthesis using conditional GANs. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 3501\u20133510 (2018)","DOI":"10.1109\/CVPR.2018.00369"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Regmi, K., Shah, M.: Bridging the domain gap for ground-to-aerial image matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 470\u2013479 (2019)","DOI":"10.1109\/ICCV.2019.00056"},{"key":"20_CR31","unstructured":"Ren, B., Tang, H., Sebe, N.: Cascaded cross MLP-mixer GANs for cross-view image translation. arXiv preprint arXiv:2110.10183 (2021)"},{"issue":"1","key":"20_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3544777","volume":"42","author":"D Roich","year":"2022","unstructured":"Roich, D., Mokady, R., Bermano, A.H., Cohen-Or, D.: Pivotal tuning for latent-based editing of real images. ACM Trans. Graph. (TOG) 42(1), 1\u201313 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. arXiv preprint arXiv:2208.12242 (2022)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Shi, Y., Wu, F., Perincherry, A., Vora, A., Li, H.: Boosting 3-dof ground-to-satellite camera localization accuracy via geometry-guided cross-view transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21516\u201321526 (2023)","DOI":"10.1109\/ICCV51070.2023.01967"},{"key":"20_CR37","unstructured":"Singh, S.K., Naidu, S.D., Srinivasan, T., Krishna, B.G., Srivastava, P.: Rational polynomial modelling for cartosat-1 data. Int. Arch. Photogrammetry Remote Sens. Spatial Inf. Sci. 37(Part B1), 885\u2013888 (2008)"},{"key":"20_CR38","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"20_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-319-46448-0_30","volume-title":"Computer Vision \u2013 ECCV 2016","author":"NN Vo","year":"2016","unstructured":"Vo, N.N., Hays, J.: Localizing and orienting street views using overhead imagery. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 494\u2013509. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_30"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Workman, S., Souvenir, R., Jacobs, N.: Wide-area image geolocalization with aerial reference imagery. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3961\u20133969 (2015)","DOI":"10.1109\/ICCV.2015.451"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Cross-view panorama image synthesis. IEEE Trans. Multimedia 25, 3546\u20133559 (2022)","DOI":"10.1109\/TMM.2022.3162474"},{"key":"20_CR42","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":"20_CR43","doi-asserted-by":"publisher","first-page":"275","DOI":"10.5194\/isprs-annals-X-1-2024-275-2024","volume":"10","author":"N Xu","year":"2024","unstructured":"Xu, N., Qin, R.: Large-scale DSM registration via motion averaging. ISPRS Ann. Photogrammetry Remote Sens. Spatial Inf. Sci. 10, 275\u2013282 (2024)","journal-title":"ISPRS Ann. Photogrammetry Remote Sens. Spatial Inf. Sci."},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Xu, N., Qin, R., Huang, D., Remondino, F.: Multi-tiling neural radiance field (nerf)\u2013geometric assessment on large-scale aerial datasets. The Photogrammetric Record (2024)","DOI":"10.1111\/phor.12498"},{"key":"20_CR45","doi-asserted-by":"publisher","first-page":"100032","DOI":"10.1016\/j.ophoto.2023.100032","volume":"8","author":"N Xu","year":"2023","unstructured":"Xu, N., Qin, R., Song, S.: Point cloud registration for lidar and photogrammetric data: a critical synthesis and performance analysis on classic and deep learning algorithms. ISPRS Open J. Photogrammetry Remote Sens. 8, 100032 (2023)","journal-title":"ISPRS Open J. Photogrammetry Remote Sens."},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, S., Yang, T., Chen, C.: Vigor: cross-view image geo-localization beyond one-to-one retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3640\u20133649 (2021)","DOI":"10.1109\/CVPR46437.2021.00364"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72970-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:17:30Z","timestamp":1732274250000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}