{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:09:43Z","timestamp":1771956583150,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730382","type":"print"},{"value":"9783031730399","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73039-9_1","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Depth-Guided NeRF Training via\u00a0Earth Mover\u2019s Distance"],"prefix":"10.1007","author":[{"given":"Anita","family":"Rau","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josiah","family":"Aklilu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F.","family":"Christopher Holsinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serena","family":"Yeung-Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"issue":"2","key":"1_CR1","doi-asserted-by":"publisher","first-page":"4606","DOI":"10.1109\/LRA.2022.3150497","volume":"7","author":"M Adamkiewicz","year":"2022","unstructured":"Adamkiewicz, M., et al.: Vision-only robot navigation in a neural radiance world. IEEE Rob. Autom. Lett. 7(2), 4606\u20134613 (2022)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"1_CR2","doi-asserted-by":"publisher","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: ZoeDepth: zero-shot transfer by combining relative and metric depth (2023). https:\/\/doi.org\/10.48550\/ARXIV.2302.12288. https:\/\/arxiv.org\/abs\/2302.12288","DOI":"10.48550\/ARXIV.2302.12288"},{"key":"1_CR3","unstructured":"Blukis, V., et al.: One-shot neural fields for 3D object understanding. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) on XRNeRF: Advances in NeRF for the Metaverse 2023. IEEE\/CVF (2023)"},{"key":"1_CR4","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. arXiv preprint arXiv:1301.3572 (2013)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"1_CR6","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":"1_CR7","unstructured":"Feydy, J., S\u00e9journ\u00e9, T., Vialard, F.X., Amari, S.I., Trouv\u00e9, A., Peyr\u00e9, G.: Interpolating between optimal transport and MMD using Sinkhorn divergences. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 2681\u20132690. PMLR (2019)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Wang, G., Chen, Z., Loy, C.C., Liu, Z.: SparseNeRF: distilling depth ranking for few-shot novel view synthesis. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00832"},{"key":"1_CR9","doi-asserted-by":"publisher","unstructured":"Jain, A., Tancik, M., Abbeel, P.: Putting nerf on a diet: semantically consistent few-shot view synthesis. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5865\u20135874. IEEE Computer Society, Los Alamitos, CA, USA, October 2021. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00583. https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICCV48922.2021.00583","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: DDP: diffusion model for dense visual prediction (2023)","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"1_CR11","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? (2017)"},{"issue":"6","key":"1_CR12","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1007\/s11633-023-1458-0","volume":"20","author":"Z Li","year":"2023","unstructured":"Li, Z., Chen, Z., Liu, X., Jiang, J.: DepthFormer: exploiting long-range correlation and local information for accurate monocular depth estimation. Mach. Intell. Res. 20(6), 837\u2013854 (2023)","journal-title":"Mach. Intell. Res."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","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. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Barron, J.T., Mildenhall, B., Sajjadi, M.S.M., Geiger, A., Radwan, N.: RegNeRF: regularizing neural radiance fields for view synthesis from sparse inputs. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"1_CR16","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Prinzler, M., Hilliges, O., Thies, J.: DINER: depth-aware image-based neural radiance fields. In: Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01198"},{"key":"1_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"1_CR20","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 Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR21","doi-asserted-by":"publisher","unstructured":"Roessle, B., Barron, J.T., Mildenhall, B., Srinivasan, P.P., Niebner, M.: Dense depth priors for neural radiance fields from sparse input views. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12882\u201312891. IEEE Computer Society, Los Alamitos, CA, USA, June 2022. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01255. https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52688.2022.01255","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"1_CR22","unstructured":"Saxena, S., Kar, A., Norouzi, M., Fleet, D.J.: Monocular depth estimation using diffusion models (2023)"},{"key":"1_CR23","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":"1_CR24","unstructured":"Song, J., et al.: D\u00e4rf: boosting radiance fields from sparse inputs with monocular depth adaptation. In: Proceedings of the 37th International Conference on Neural Information Processing Systems, pp. 68458\u201368470 (2023)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Martin-Brualla, R., Guibas, L., Li, K.: SCADE: NeRFs from space carving with ambiguity-aware depth estimates. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01585"},{"key":"1_CR26","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-031-16449-1_41","volume-title":"MICCAI 2022","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Long, Y., Fan, S.H., Dou, Q.: Neural rendering for stereo 3D reconstruction of deformable tissues in robotic surgery. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13437, pp. 431\u2013441. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_41"},{"key":"1_CR27","doi-asserted-by":"publisher","unstructured":"Wei, Y., Liu, S., Rao, Y., Zhao, W., Lu, J., Zhou, J.: NerfingMVS: guided optimization of neural radiance fields for indoor multi-view stereo. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5590\u20135599. IEEE Computer Society, Los Alamitos, CA, USA, October 2021. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00556. https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICCV48922.2021.00556","DOI":"10.1109\/ICCV48922.2021.00556"},{"key":"1_CR28","doi-asserted-by":"publisher","unstructured":"Xie, Z., Geng, Z., Hu, J., Zhang, Z., Hu, H., Cao, Y.: Revealing the dark secrets of masked image modeling. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14475\u201314485. IEEE Computer Society, Los Alamitos, CA, USA, June 2023. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01391. https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52729.2023.01391","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Metric3D: towards zero-shot metric 3D prediction from a single image (2023)","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"1_CR31","doi-asserted-by":"publisher","unstructured":"Yin, W., et al.: Learning to recover 3D scene shape from a single image. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 204\u2013213 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00027","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"1_CR32","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 (CVPR) (2021). http:\/\/arxiv.org\/abs\/2012.02190v3","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"1_CR33","doi-asserted-by":"publisher","unstructured":"Yuan, W., Gu, X., Dai, Z., Zhu, S., Tan, P.: Neural window fully-connected CRFs for monocular depth estimation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3906\u20133915. IEEE Computer Society, Los Alamitos, CA, USA, June 2022. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00389. https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52688.2022.00389","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"1_CR34","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":"1_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: NICE-SLAM: neural implicit scalable encoding for slam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12786\u201312796 (2022)","DOI":"10.1109\/CVPR52688.2022.01245"}],"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\/978-3-031-73039-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:15:17Z","timestamp":1730301317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73039-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730382","9783031730399"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73039-9_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 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"}}]}}