{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:46:11Z","timestamp":1777653971713,"version":"3.51.4"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734038","type":"print"},{"value":"9783031734045","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-73404-5_6","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T16:03:13Z","timestamp":1730217793000},"page":"90-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Depth-Guided Urban View Synthesis"],"prefix":"10.1007","author":[{"given":"Sheng","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongfeng","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weichao","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingbing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyi","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"6_CR1","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"6_CR2","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. arXiv preprint arXiv:2304.06706 (2023)","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: MVSNERF: fast generalizable radiance field reconstruction from multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14124\u201314133 (2021)","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"6_CR4","unstructured":"Cheng, K., et al.: UC-NeRF: neural radiance field for under-calibrated multi-view cameras. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Deng, K., Liu, A., Zhu, J.Y., Ramanan, D.: Depth-supervised NeRF: fewer views and faster training for free. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12882\u201312891 (2022)","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"6_CR7","unstructured":"Fu, X., et al.: PanopticNeRF-360: Panoramic 3D-to-2D label transfer in urban scenes. arXiv preprint arXiv:2309.10815 (2023)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Panoptic NeRF: 3D-to-2D label transfer for panoptic urban scene segmentation. In: 2022 International Conference on 3D Vision (3DV), pp. 1\u201311. IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"6_CR9","unstructured":"Guo, J., et al.: StreetSurf: extending multi-view implicit surface reconstruction to street views. arXiv preprint arXiv:2306.04988 (2023)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19740\u201319750 (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Huang, D., Peng, S., He, T., Yang, H., Zhou, X., Ouyang, W.: Ponder: point cloud pre-training via neural rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16089\u201316098 (2023)","DOI":"10.1109\/ICCV51070.2023.01474"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., et al.: NeO 360: neural fields for sparse view synthesis of outdoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9187\u20139198 (2023)","DOI":"10.1109\/ICCV51070.2023.00843"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Jain, A., Tancik, M., Abbeel, P.: Putting NeRF on a diet: semantically consistent few-shot view synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5885\u20135894 (2021)","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Johari, M.M., Lepoittevin, Y., Fleuret, F.: GeoNeRF: generalizing NeRF with geometry priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18365\u201318375 (2022)","DOI":"10.1109\/CVPR52688.2022.01782"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"6_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Kundu, A., et al.: Panoptic neural fields: a semantic object-aware neural scene representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12871\u201312881 (2022)","DOI":"10.1109\/CVPR52688.2022.01253"},{"issue":"2","key":"6_CR19","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1609\/aaai.v37i2.25238","volume":"37","author":"Z Li","year":"2023","unstructured":"Li, Z., Li, L., Zhu, J.: READ: large-scale neural scene rendering for autonomous driving. Proc. AAAI Conf. Artif. Intell. 37(2), 1522\u20131529 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i2.25238","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"3","key":"6_CR20","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 Trans. Pattern Anal. Mach. Intell. 45(3), 3292\u20133310 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR21","first-page":"15651","volume":"33","author":"L Liu","year":"2020","unstructured":"Liu, L., Gu, J., Zaw Lin, K., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. Adv. Neural. Inf. Process. Syst. 33, 15651\u201315663 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Neural rays for occlusion-aware image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7824\u20137833 (2022)","DOI":"10.1109\/CVPR52688.2022.00767"},{"key":"6_CR23","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137219 (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"issue":"1","key":"6_CR24","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","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 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"6_CR25","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5480\u20135490 (2022)","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Ost, J., Mannan, F., Thuerey, N., Knodt, J., Heide, F.: Neural scene graphs for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2856\u20132865 (2021)","DOI":"10.1109\/CVPR46437.2021.00288"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"6_CR28","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Rematas, K., et al.: Urban radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12932\u201312942 (2022)","DOI":"10.1109\/CVPR52688.2022.01259"},{"issue":"4","key":"6_CR30","first-page":"1","volume":"41","author":"D R\u00fcckert","year":"2022","unstructured":"R\u00fcckert, D., Franke, L., Stamminger, M.: ADOP: approximate differentiable one-pixel point rendering. ACM Trans. Graph. (ToG) 41(4), 1\u201314 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Seo, S., Han, D., Chang, Y., Kwak, N.: MixNeRF: modeling a ray with mixture density for novel view synthesis from sparse inputs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20659\u201320668 (2023)","DOI":"10.1109\/CVPR52729.2023.01979"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Shamsafar, F., Woerz, S., Rahim, R., Zell, A.: MobileStereoNet: towards lightweight deep networks for stereo matching. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2417\u20132426 (2022)","DOI":"10.1109\/WACV51458.2022.00075"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.T.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.T.: Improved direct voxel grid optimization for radiance fields reconstruction. arXiv preprint arXiv:2206.05085 (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: 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":"6_CR37","doi-asserted-by":"crossref","unstructured":"Tancik, M., et al.: Block-NeRF: scalable large scene neural view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8248\u20138258 (2022)","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"6_CR38","unstructured":"Tao, A., Sapra, K., Catanzaro, B.: Hierarchical multi-scale attention for semantic segmentation. arXiv preprint arXiv:2005.10821 (2020)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Wang, G., Chen, Z., Loy, C.C., Liu, Z.: SparseNeRF: distilling depth ranking for few-shot novel view synthesis. arXiv preprint arXiv:2303.16196 (2023)","DOI":"10.1109\/ICCV51070.2023.00832"},{"key":"6_CR40","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: F2-NeRF: fast neural radiance field training with free camera trajectories. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4150\u20134159 (2023)","DOI":"10.1109\/CVPR52729.2023.00404"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"6_CR43","doi-asserted-by":"publisher","unstructured":"Wu, Z., et\u00a0al.: MARS: an instance-aware, modular and realistic simulator for autonomous driving. In: CAAI International Conference on Artificial Intelligence, pp. 3\u201315. Springer (2023). https:\/\/doi.org\/10.1007\/978-981-99-8850-1_1","DOI":"10.1007\/978-981-99-8850-1_1"},{"key":"6_CR44","unstructured":"Xie, Z., Zhang, J., Li, W., Zhang, F., Zhang, L.: S-NeRF: neural radiance fields for street views. arXiv preprint arXiv:2303.00749 (2023)"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: MuRF: multi-baseline radiance fields. arXiv preprint arXiv:2312.04565 (2023)","DOI":"10.1109\/CVPR52733.2024.01894"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Xu, Q., et al.: Point-NeRF: point-based neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5438\u20135448 (2022)","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Yang, H., et\u00a0al.: UniPAD: a universal pre-training paradigm for autonomous driving. arXiv preprint arXiv:2310.08370 (2023)","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"6_CR48","unstructured":"Yang, J., et\u00a0al.: EmerNeRF: emergent spatial-temporal scene decomposition via self-supervision. arXiv preprint arXiv:2311.02077 (2023)"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Yang, J., Pavone, M., Wang, Y.: FreeNeRF: improving few-shot neural rendering with free frequency regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8254\u20138263 (2023)","DOI":"10.1109\/CVPR52729.2023.00798"},{"key":"6_CR50","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. arXiv preprint arXiv:2401.10891 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"6_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Y., Yang, Y., Guo, H., Xiong, R., Wang, Y., Liao, Y.: UrbanGIRAFFE: representing urban scenes as compositional generative neural feature fields. arXiv preprint arXiv:2303.14167 (2023)","DOI":"10.1109\/ICCV51070.2023.00844"},{"key":"6_CR52","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: UniSim: a neural closed-loop sensor simulator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1389\u20131399 (2023)","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"6_CR53","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"6_CR54","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":"6_CR55","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"6_CR56","unstructured":"Zhu, H., et\u00a0al.: PonderV2: pave the way for 3D foundataion model with a universal pre-training paradigm. arXiv preprint arXiv:2310.08586 (2023)"}],"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\/978-3-031-73404-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T19:45:23Z","timestamp":1745523923000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73404-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031734038","9783031734045"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73404-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 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"}}]}}