{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:21:44Z","timestamp":1792689704320,"version":"4.5.0"},"publisher-location":"Cham","reference-count":121,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376268","type":"print"},{"value":"9783032376275","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\/978-3-032-37627-5_24","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:01:47Z","timestamp":1788984107000},"page":"431-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from\u00a0Satellite Imagery"],"prefix":"10.1007","author":[{"given":"Jie-Ying","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Ruei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shr-Ruei","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Cheng","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Ho","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiewen","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenjun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chieh Hubert","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Lun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: Mip-NeRF: a multiscale representation for anti-aliasing neural radiance fields (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-NeRF 360: unbounded anti-aliased neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Zip-NeRF: anti-aliased grid-based neural radiance fields. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"24_CR4","unstructured":"Binkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: International Conference on Learning Representations (2018)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Bosch, M., Kurtz, Z., Hagstrom, S., Brown, M.: A multiple view stereo benchmark for satellite imagery. In: 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pp.\u00a01\u20139. IEEE (2016)","DOI":"10.1109\/AIPR.2016.8010543"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"24_CR7","unstructured":"Chen, H., et al.: VI3DRM: towards meticulous 3D reconstruction from sparse views via photo-realistic novel view synthesis (2024). https:\/\/arxiv.org\/abs\/2409.08207"},{"key":"24_CR8","doi-asserted-by":"publisher","first-page":"34487","DOI":"10.52202\/079017-1087","volume":"37","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Lee, G.H.: DOGS: distributed-oriented gaussian splatting for large-scale 3D reconstruction via Gaussian consensus. Adv. Neural. Inf. Process. Syst. 37, 34487\u201334512 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR9","unstructured":"Chung, J., Lee, S., Nam, H., Lee, J., Lee, K.M.: LucidDreamer: domain-free generation of 3D gaussian splatting scenes. arXiv preprint arXiv:2311.13384 (2023)"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Dahmani, H., Bennehar, M., Piasco, N., Roldao, L., Tsishkou, D.: SWAG: splatting in the wild images with appearance-conditioned Gaussians (2024). https:\/\/arxiv.org\/abs\/2403.10427","DOI":"10.1007\/978-3-031-73116-7_19"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Deng, B., Tucker, R., Li, Z., Guibas, L., Snavely, N., Wetzstein, G.: StreetScapes: large-scale consistent street view generation using autoregressive video diffusion. In: SIGGRAPH 2024 Conference Papers (2024)","DOI":"10.1145\/3641519.3657513"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Derksen, D., Izzo, D.: Shadow neural radiance fields for multi-view satellite photogrammetry. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 1152\u20131161 (2021)","DOI":"10.1109\/CVPRW53098.2021.00126"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Dihlmann, J.N., Engelhardt, A., Lensch, H.P.: SIGNeRF: scene integrated generation for neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00638"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Fan, C.D., et al.: SpectroMotion: dynamic 3D reconstruction of specular scenes. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21328\u201321338 (2025)","DOI":"10.1109\/CVPR52734.2025.01987"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Fang, J., Wang, J., Zhang, X., Xie, L., Tian, Q.: GaussianEditor: editing 3D Gaussians delicately with text instructions. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01975"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Gao, J., Liu, J., Ji, S.: Rational polynomial camera model warping for deep learning based satellite multi-view stereo matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6148\u20136157 (2021)","DOI":"10.1109\/ICCV48922.2021.00609"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Gao, J., Liu, J., Ji, S.: A general deep learning based framework for 3D reconstruction from multi-view stereo satellite images. ISPRS J. Photogramm. Remote. Sens. 195, 446\u2013461 (2023)","DOI":"10.1016\/j.isprsjprs.2022.12.012"},{"key":"24_CR18","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1016\/j.isprsjprs.2022.12.012","volume":"195","author":"J Gao","year":"2023","unstructured":"Gao, J., Liu, J., Ji, S.: A general deep learning based framework for 3D reconstruction from multi-view stereo satellite images. ISPRS J. Photogramm. Remote. Sens. 195, 446\u2013461 (2023)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Gao, K., Lu, D., He, H., Xu, L., Li, J.: Enhanced 3D urban scene reconstruction and point cloud densification using gaussian splatting and google earth imagery (2024). https:\/\/arxiv.org\/abs\/2405.11021","DOI":"10.1109\/TGRS.2025.3536169"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Gao, R., et al.: CAT3D: create anything in 3D with multi-view diffusion models. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-2403"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: CityGS-X: a scalable architecture for efficient and geometrically accurate large-scale scene reconstruction (2025). https:\/\/arxiv.org\/abs\/2503.23044","DOI":"10.1109\/ICCV51701.2025.02524"},{"key":"24_CR22","unstructured":"Google: Google earth studio. https:\/\/earth.google.com\/studio (2024). Accessed 14 May 2025"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"24_CR24","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"24_CR25","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, pp. 6626\u20136637 (2017)"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Hou, H.Y., et al.: 3D gaussian splatting with grouped uncertainty for unconstrained images. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10887619"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Hua, T., Jiang, L., Chen, Y.C., Zhao, W.: Sat2City: 3D city generation from a single satellite image with cascaded latent diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 27978\u201327988 (2025)","DOI":"10.1109\/ICCV51701.2025.02597"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: SkySplat: generalizable 3D gaussian splatting from multi-temporal sparse satellite images. arXiv preprint arXiv:2508.09479 (2025)","DOI":"10.1609\/aaai.v40i7.37430"},{"issue":"13","key":"24_CR29","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1049\/el:20080522","volume":"44","author":"Q Huynh-Thu","year":"2008","unstructured":"Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image\/video quality assessment. Electron. Lett. 44(13), 800\u2013801 (2008)","journal-title":"Electron. Lett."},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking FID: towards a better evaluation metric for image generation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, L., et al.: Horizon-GS: unified 3D Gaussian splatting for large-scale aerial-to-ground scenes. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26789\u201326799 (2025)","DOI":"10.1109\/CVPR52734.2025.02495"},{"key":"24_CR32","unstructured":"Kang, Y., Wang, X., Wu, Z., Shi, Y., Zhu, H.: Sat2RealCity: geometry-aware and appearance-controllable 3D urban generation from satellite imagery (2025). https:\/\/arxiv.org\/abs\/2511.11470"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. In: ACM TOG (2023)","DOI":"10.1145\/3592433"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Meuleman, A., Kopanas, G., Wimmer, M., Lanvin, A., Drettakis, G.: A hierarchical 3D Gaussian representation for real-time rendering of very large datasets. In: ACM TOG (2024)","DOI":"10.1145\/3658160"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Kulhanek, J., Peng, S., Kukelova, Z., Pollefeys, M., Sattler, T.: WildGaussians: 3D Gaussian splatting in the wild. In: NeurIPS (2024)","DOI":"10.52202\/079017-0670"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Kulikov, V., Kleiner, M., Huberman-Spiegelglas, I., Michaeli, T.: FlowEdit: Inversion-free text-based editing using pre-trained flow models. arXiv preprint arXiv:2412.08629 (2024)","DOI":"10.1109\/ICCV51701.2025.01834"},{"key":"24_CR37","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Aittala, M., Aila, T., Lehtinen, J.: The role of imagenet classes in fr\u00e9chet inception distance. In: Proceedings ICLR (2023)"},{"key":"24_CR38","unstructured":"Labs, B.F.: FLUX. https:\/\/github.com\/black-forest-labs\/flux (2024). Accessed 28 Feb 2025"},{"key":"24_CR39","unstructured":"Labs, B.F.: Official weights of FLUX.1 dev. https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-dev (2024). Accessed 28 Feb 2025"},{"key":"24_CR40","doi-asserted-by":"publisher","unstructured":"Le\u00a0Saux, B., Yokoya, N., H\u00e4nsch, R., Brown, M.: Data fusion contest 2019 (DFC2019) (2019). https:\/\/doi.org\/10.21227\/c6tm-vw12","DOI":"10.21227\/c6tm-vw12"},{"key":"24_CR41","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 (2019)","DOI":"10.1109\/CVPRW.2019.00186"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: DNGaussian: optimizing sparse-view 3D gaussian radiance fields with global-local depth normalization. arXiv preprint arXiv:2403.06912 (2024)","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"24_CR43","unstructured":"Li, W., et al.: CrossViewDiff: a cross-view diffusion model for satellite-to-street view synthesis (2024). https:\/\/arxiv.org\/abs\/2408.14765"},{"key":"24_CR44","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7141\u20137150 (2024)","DOI":"10.1109\/CVPR52733.2024.00682"},{"key":"24_CR45","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 (2021). https:\/\/arxiv.org\/abs\/2012.06628","DOI":"10.1109\/ICCV48922.2021.01221"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: InfiniCity: infinite-scale city synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.02085"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., et al.: FrugalNeRF: fast convergence for extreme few-shot novel view synthesis without learned priors. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 11227\u201311238 (2025)","DOI":"10.1109\/CVPR52734.2025.01049"},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: VastGaussian: vast 3D Gaussians for large scene reconstruction (2024). https:\/\/arxiv.org\/abs\/2402.17427","DOI":"10.1109\/CVPR52733.2024.00494"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Liu, K.H., Yang, C.K., Chen, M.H., Liu, Y.L., Lin, Y.Y.: Corrfill: enhancing faithfulness in reference-based inpainting with correspondence guidance in diffusion models. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1618\u20131627. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00165"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. In: CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Liu, T., Zhao, S., Jiang, W., Guo, B.: Sat-DN: implicit surface reconstruction from multi-view satellite images with depth and normal supervision (2025). https:\/\/arxiv.org\/abs\/2502.08352","DOI":"10.1109\/JSTARS.2025.3607020"},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Liu, X., Chen, J., Kao, S.H., Tai, Y.W., Tang, C.K.: Deceptive-NeRF\/3DGS: diffusion-generated pseudo-observations for high-quality sparse-view reconstruction. arXiv preprint arXiv:2305.15171 (2023)","DOI":"10.1007\/978-3-031-72640-8_19"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Liu, Y., Luo, C., Fan, L., Wang, N., Peng, J., Zhang, Z.: CityGaussian: real-time high-quality large-scale scene rendering with gaussians. In: European Conference on Computer Vision, pp. 265\u2013282. Springer (2025)","DOI":"10.1007\/978-3-031-72640-8_15"},{"key":"24_CR55","unstructured":"Liu, Y., Luo, C., Mao, Z., Peng, J., Zhang, Z.: CityGaussianV2: efficient and geometrically accurate reconstruction for large-scale scenes (2024). https:\/\/arxiv.org\/abs\/2411.00771"},{"key":"24_CR56","doi-asserted-by":"crossref","unstructured":"Mar\u00ed, R., Facciolo, G., Ehret, T.: Sat-NeRF: learning multi-view satellite photogrammetry with transient objects and shadow modeling using RPC cameras. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1310\u20131320 (2022)","DOI":"10.1109\/CVPRW56347.2022.00137"},{"key":"24_CR57","doi-asserted-by":"crossref","unstructured":"Mar\u00ed, R., Facciolo, G., Ehret, T.: Multi-date earth observation NeRF: the detail is in the shadows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2034\u20132044 (2023)","DOI":"10.1109\/CVPRW59228.2023.00197"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"24_CR59","unstructured":"Melas-Kyriazi, L., et al.: IM-3D: iterative multiview diffusion and reconstruction for high-quality 3D generation. In: rnational Conference on Machine Learning (2024)"},{"key":"24_CR60","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2022)"},{"key":"24_CR61","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM (2021)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"24_CR62","doi-asserted-by":"crossref","unstructured":"Mirzaei, A., et al.: Watch your steps: local image and scene editing by text instructions. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72920-1_7"},{"key":"24_CR63","doi-asserted-by":"crossref","unstructured":"Mirzaei, A., et al.: Spin-NeRF: multiview segmentation and perceptual inpainting with neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20669\u201320679 (2023)","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"24_CR64","doi-asserted-by":"crossref","unstructured":"Miyake, D., Iohara, A., Saito, Y., Tanaka, T.: Negative-prompt inversion: fast image inversion for editing with text-guided diffusion models (2024). https:\/\/arxiv.org\/abs\/2305.16807","DOI":"10.1109\/WACV61041.2025.00207"},{"key":"24_CR65","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: null-text inversion for editing real images using guided diffusion models. arXiv preprint arXiv:2211.09794 (2022)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"24_CR66","doi-asserted-by":"publisher","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. 41(4), 102:1\u2013102:15 (2022). https:\/\/doi.org\/10.1145\/3528223.3530127","DOI":"10.1145\/3528223.3530127"},{"key":"24_CR67","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Barron, J.T., Mildenhall, B., Sajjadi, M.S., Geiger, A., Radwan, N.: RegNeRF: regularizing neural radiance fields for view synthesis from sparse inputs. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"24_CR68","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"24_CR69","doi-asserted-by":"publisher","unstructured":"Qian, M., et al.: Seeing through satellite images at street views. IEEE Trans. Pattern Anal. Mach. Intell., 1\u201318 (2026). https:\/\/doi.org\/10.1109\/TPAMI.2026.3652860","DOI":"10.1109\/TPAMI.2026.3652860"},{"key":"24_CR70","unstructured":"Qian, M., et al.: Sat3DGen: comprehensive street-level 3D scene generation from single satellite image. In: International Conference on Learning Representations (ICLR) (2026)"},{"key":"24_CR71","doi-asserted-by":"crossref","unstructured":"Qian, M., Xiong, J., Xia, G.S., Xue, N.: Sat2Density: faithful density learning from satellite-ground image pairs. In: IEEE\/CVF International Conference on Computer Vision (ICCV) 2023)","DOI":"10.1109\/ICCV51070.2023.00341"},{"key":"24_CR72","doi-asserted-by":"publisher","unstructured":"Qu, Y., Deng, F.: Sat-Mesh: Learning neural implicit surfaces for multi-view satellite reconstruction. Remote Sens. 15(17) (2023). https:\/\/doi.org\/10.3390\/rs15174297, https:\/\/www.mdpi.com\/2072-4292\/15\/17\/4297","DOI":"10.3390\/rs15174297"},{"key":"24_CR73","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"24_CR74","doi-asserted-by":"crossref","unstructured":"Regmi, K., Borji, A.: Cross-view image synthesis using conditional GANs (2018). https:\/\/arxiv.org\/abs\/1803.03396","DOI":"10.1109\/CVPR.2018.00369"},{"key":"24_CR75","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR76","doi-asserted-by":"crossref","unstructured":"Sabour, S., et al.: SpotLessSplats: ignoring distractors in 3D gaussian splatting. arXiv preprint arXiv:2406.20055 (2024)","DOI":"10.1145\/3727143"},{"key":"24_CR77","doi-asserted-by":"crossref","unstructured":"Savant Aira, L., Facciolo, G., Ehret, T.: Gaussian splatting for efficient satellite image photogrammetry. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.00559"},{"key":"24_CR78","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"24_CR79","unstructured":"Shang, Y., et al.: UrbanWorld: an urban world model for 3D city generation. arXiv preprint arXiv:2407.11965 (2024)"},{"key":"24_CR80","doi-asserted-by":"crossref","unstructured":"Shen, J., Agudo, A., Moreno-Noguer, F., Ruiz, A.: Conditional-flow NeRF: accurate 3D modelling with reliable uncertainty quantification. In: European Conference on Computer Vision, pp. 540\u2013557. Springer (2022)","DOI":"10.1007\/978-3-031-20062-5_31"},{"key":"24_CR81","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"issue":"12","key":"24_CR82","doi-asserted-by":"publisher","first-page":"10009","DOI":"10.1109\/TPAMI.2022.3140750","volume":"44","author":"Y Shi","year":"2022","unstructured":"Shi, Y., Campbell, D., Yu, X., Li, H.: Geometry-guided street-view panorama synthesis from satellite imagery. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 10009\u201310022 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR83","doi-asserted-by":"crossref","unstructured":"Shriram, J., Trevithick, A., Liu, L., Ramamoorthi, R.: RealmDreamer: text-driven 3D scene generation with inpainting and depth diffusion. In: International Conference on 3D Vision (3DV) (2025)","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"24_CR84","doi-asserted-by":"crossref","unstructured":"Sprintson, M., Chellappa, R., Peng, C.: FusionRF: high-fidelity satellite neural radiance fields from multispectral and panchromatic acquisitions. arXiv preprint arXiv:2409.15132 (2024)","DOI":"10.1109\/JSTSP.2025.3628532"},{"key":"24_CR85","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"24_CR86","doi-asserted-by":"crossref","unstructured":"Tancik, M., et al.: Block-NeRF: scalable large scene neural view synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"24_CR87","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative gaussian splatting for efficient 3D content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"24_CR88","doi-asserted-by":"crossref","unstructured":"Toker, A., Zhou, Q., Maximov, M., Leal-Taix\u00e9, L.: Coming down to earth: satellite-to-street view synthesis for geo-localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6488\u20136497 (2021)","DOI":"10.1109\/CVPR46437.2021.00642"},{"key":"24_CR89","doi-asserted-by":"crossref","unstructured":"Turki, H., Ramanan, D., Satyanarayanan, M.: Mega-NeRF: scalable construction of large-scale NeRFs for virtual fly-throughs. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01258"},{"key":"24_CR90","unstructured":"Wang, R., et al.: MoGe: unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision (2024). https:\/\/arxiv.org\/abs\/2410.19115"},{"key":"24_CR91","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yi, X., Wu, Z., Zhao, N., Chen, L., Zhang, H.: View-consistent 3D editing with Gaussian splatting (2025). https:\/\/arxiv.org\/abs\/2403.11868","DOI":"10.1007\/978-3-031-72761-0_23"},{"key":"24_CR92","unstructured":"Wang, Y., Wang, J., Qi, Y.: WE-GS: an in-the-wild efficient 3D gaussian representation for unconstrained photo collections (2024). https:\/\/arxiv.org\/abs\/2406.02407"},{"key":"24_CR93","doi-asserted-by":"publisher","first-page":"8406","DOI":"10.52202\/075280-0368","volume":"36","author":"Z Wang","year":"2023","unstructured":"Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. Adv. Neural. Inf. Process. Syst. 36, 8406\u20138441 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"24_CR94","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR95","doi-asserted-by":"crossref","unstructured":"Weber, E., et al.: NeRFiller: completing scenes via generative 3D inpainting. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01959"},{"key":"24_CR96","doi-asserted-by":"crossref","unstructured":"Wu, C.H., et al.: AuraFusion360: augmented unseen region alignment for reference-based 360$$ ^\\circ $$ unbounded scene inpainting (2025). https:\/\/arxiv.org\/abs\/2502.05176","DOI":"10.1109\/CVPR52734.2025.01526"},{"key":"24_CR97","doi-asserted-by":"crossref","unstructured":"Wu, J., Bian, J.W., Li, X., Wang, G., Reid, I., Torr, P., Prisacariu, V.: GaussCtrl: multi-view consistent text-driven 3D gaussian splatting editing. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72630-9_4"},{"key":"24_CR98","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: CAT4D: create anything in 4D with multi-view video diffusion models (2024). https:\/\/arxiv.org\/abs\/2411.18613","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"24_CR99","unstructured":"Wu, R., et al.: ReconFusion: 3D reconstruction with diffusion priors. arXiv preprint arXiv:2312.02981 (2023)"},{"key":"24_CR100","unstructured":"Wu, Y., Liu, J., Ji, S.: 3D Gaussian splatting for large-scale surface reconstruction from aerial images (2024). https:\/\/arxiv.org\/abs\/2409.00381"},{"key":"24_CR101","doi-asserted-by":"crossref","unstructured":"Xie, H., Chen, Z., Hong, F., Liu, Z.: CityDreamer: compositional generative model of unbounded 3D cities. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00923"},{"key":"24_CR102","doi-asserted-by":"crossref","unstructured":"Xie, H., Chen, Z., Hong, F., Liu, Z.: CityDreamer4D: compositional generative model of unbounded 4D cities. arXiv preprint arXiv:2501.08983 (2025)","DOI":"10.1109\/TPAMI.2025.3603078"},{"key":"24_CR103","doi-asserted-by":"crossref","unstructured":"Xie, H., Chen, Z., Hong, F., Liu, Z.: Generative gaussian splatting for unbounded 3D city generation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00573"},{"key":"24_CR104","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, Y., Patel, V.M.: Wild-GS: real-time novel view synthesis from unconstrained photo collections (2024). https:\/\/arxiv.org\/abs\/2406.10373","DOI":"10.52202\/079017-3283"},{"key":"24_CR105","doi-asserted-by":"crossref","unstructured":"Xu, N., Qin, R.: Geospecific view generation geometry-context aware high-resolution ground view inference from satellite views. In: European Conference on Computer Vision, pp. 349\u2013366. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_20"},{"key":"24_CR106","doi-asserted-by":"crossref","unstructured":"Xu, N., Qin, R.: Satellite to groundscape-large-scale consistent ground view generation from satellite views. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6068\u20136077 (2025)","DOI":"10.1109\/CVPR52734.2025.00569"},{"key":"24_CR107","doi-asserted-by":"crossref","unstructured":"Yao, X., Wang, X., Wu, H., Ping, C., Zhang, D., Xiong, H.: MagicCity: geometry-aware 3D city generation from satellite imagery with multi-view consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25325\u201325334 (2025)","DOI":"10.1109\/ICCV51701.2025.02349"},{"key":"24_CR108","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: segment and edit anything in 3D scenes. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"24_CR109","doi-asserted-by":"crossref","unstructured":"Yi, T., et al.: GaussianDreamer: fast generation from text to 3D Gaussians by bridging 2D and 3D diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6796\u20136807 (2024)","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"24_CR110","doi-asserted-by":"crossref","unstructured":"Yu, H.X., Duan, H., Herrmann, C., Freeman, W.T., Wu, J.: WonderWorld: interactive 3D scene generation from a single image. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5916\u20135926 (2025)","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"24_CR111","doi-asserted-by":"crossref","unstructured":"Yu, Z., Chen, A., Huang, B., Sattler, T., Geiger, A.: MIP-Splatting: alias-free 3D Gaussian splatting. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"24_CR112","unstructured":"Ze, X., Song, Z., Wang, Q., Lu, J., Shi, Y.: Controllable satellite-to-street-view synthesis with precise pose alignment and zero-shot environmental control (2025). https:\/\/arxiv.org\/abs\/2502.03498"},{"key":"24_CR113","doi-asserted-by":"crossref","unstructured":"Zhang, D., Wang, C., Wang, W., Li, P., Qin, M., Wang, H.: Gaussian in the wild: 3D gaussian splatting for unconstrained image collections. arXiv preprint arXiv:2403.15704 (2024)","DOI":"10.1007\/978-3-031-73116-7_20"},{"key":"24_CR114","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, J., Yu, X., Huang, L., Gu, L., Zheng, J., Bai, X.: CoR-GS: sparse-view 3D gaussian splatting via co-regularization. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73232-4_19"},{"key":"24_CR115","doi-asserted-by":"crossref","unstructured":"Zhang, K., Sun, J., Snavely, N.: Leveraging vision reconstruction pipelines for satellite imagery. In: IEEE International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00269"},{"key":"24_CR116","unstructured":"Zhang, L., Rupnik, E.: Sparsesat-NeRF: dense depth supervised neural radiance fields for sparse satellite images. arXiv preprint arXiv:2309.00277 (2023)"},{"key":"24_CR117","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":"24_CR118","unstructured":"Zhang, S., et a;.: CityX: controllable procedural content generation for unbounded 3D cities (2024). https:\/\/arxiv.org\/abs\/2407.17572"},{"key":"24_CR119","doi-asserted-by":"crossref","unstructured":"Zhou, M., et al.: SceneX: procedural controllable large-scale scene generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 10806\u201310814 (2025)","DOI":"10.1609\/aaai.v39i10.33174"},{"key":"24_CR120","doi-asserted-by":"publisher","unstructured":"Zhou, X., Wang, Y., Lin, D., Cao, Z., Li, B., Liu, J.: SatelliteRF: accelerating 3D reconstruction in multi-view satellite images with efficient neural radiance fields. Appl. Sci. 14(7) (2024). https:\/\/doi.org\/10.3390\/app14072729, https:\/\/www.mdpi.com\/2076-3417\/14\/7\/2729","DOI":"10.3390\/app14072729"},{"key":"24_CR121","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Fan, Z., Jiang, Y., Wang, Z.: FSGS: real-time few-shot view synthesis using gaussian splatting (2023)","DOI":"10.1007\/978-3-031-72933-1_9"}],"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\/978-3-032-37627-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:02:08Z","timestamp":1788984128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37627-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376268","9783032376275"],"references-count":121,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37627-5_24","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":"10 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"}}]}}