{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:07:01Z","timestamp":1784135221906,"version":"3.55.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726637","type":"print"},{"value":"9783031726644","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72664-4_21","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"370-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":222,"title":["MVSplat: Efficient 3D Gaussian Splatting from\u00a0Sparse Multi-view Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0943-1512","authenticated-orcid":false,"given":"Yuedong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1313-3358","authenticated-orcid":false,"given":"Haofei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3584-9640","authenticated-orcid":false,"given":"Chuanxia","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0074-0303","authenticated-orcid":false,"given":"Bohan","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2448-2318","authenticated-orcid":false,"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8151-3726","authenticated-orcid":false,"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5264-2572","authenticated-orcid":false,"given":"Tat-Jen","family":"Cham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9444-3763","authenticated-orcid":false,"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Charatan, D., Li, S., Tagliasacchi, A., Sitzmann, V.: PixelSplat: 3D gaussian splats from image pairs for scalable generalizable 3D reconstruction. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, H., Esposito, S., Tang, S., Geiger, A.: LaRa: efficient large-baseline radiance fields. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73247-8_20"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: MVSNeRF: fast generalizable radiance field reconstruction from multi-view stereo. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"21_CR4","unstructured":"Chen, G., Wang, W.: A survey on 3D gaussian splatting. arXiv (2024)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xu, H., Wu, Q., Zheng, C., Cham, T.J., Cai, J.: Explicit correspondence matching for generalizable neural radiance fields. In: arXiv (2023)","DOI":"10.1109\/CVPR52729.2023.00011"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chibane, J., Bansal, A., Lazova, V., Pons-Moll, G.: Stereo radiance fields (SRF): learning view synthesis for sparse views of novel scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00782"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Collins, R.T.: A space-sweep approach to true multi-image matching. In: CVPR (1996)","DOI":"10.1109\/CVPR.1996.517097"},{"key":"21_CR8","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Ding, Y., et al.: TransMVSNet: global context-aware multi-view stereo network with transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00839"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Smith, C., Tewari, A., Sitzmann, V.: Learning to render novel views from wide-baseline stereo pairs. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"21_CR11","unstructured":"Fan, Z., et\u00a0al.: InstantSplat: unbounded sparse-view pose-free gaussian splatting in 40 seconds. arXiv (2024)"},{"key":"21_CR12","unstructured":"Gao, R., et al.: CAT3D: create anything in 3D with multi-view diffusion models. arXiv (2024)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"He, Y., Yan, R., Fragkiadaki, K., Yu, S.I.: Epipolar transformers. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00780"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Henzler, P., et al.: Unsupervised learning of 3D object categories from videos in the wild. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00467"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Jensen, R., Dahl, A., Vogiatzis, G., Tola, E., Aan\u00e6s, H.: Large scale multi-view stereopsis evaluation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.59"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Johari, M.M., Lepoittevin, Y., Fleuret, F.: GeoNeRF: generalizing NeRF with geometry priors. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01782"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. TOG 42(4), 139\u20131 (2023)","DOI":"10.1145\/3592433"},{"key":"21_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Liu, A., Tucker, R., Jampani, V., Makadia, A., Snavely, N., Kanazawa, A.: Infinite Nature: perpetual view generation of natural scenes from a single image. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Neural rays for occlusion-aware image-based rendering. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00767"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR23","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. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"21_CR24","unstructured":"Miyato, T., Jaeger, B., Welling, M., Geiger, A.: GTA: a geometry-aware attention mechanism for multi-view transformers. In: ICLR (2024)"},{"key":"21_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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common Objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: MICCAI (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., et\u00a0al.: Scene Representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"21_CR31","unstructured":"Sitzmann, V., Rezchikov, S., Freeman, B., Tenenbaum, J., Durand, F.: Light Field Networks: neural scene representations with single-evaluation rendering. NeurIPS (2021)"},{"key":"21_CR32","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene Representation Networks: continuous 3D-structure-aware neural scene representations. NeurIPS (2019)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Suhail, M., Esteves, C., Sigal, L., Makadia, A.: Generalizable patch-based neural rendering. In: ECCV (2022)","DOI":"10.1109\/CVPR52688.2022.00809"},{"key":"21_CR34","unstructured":"Szymanowicz, S., et al.: Flash3D: feed-forward generalisable 3D scene reconstruction from a single image. arxiv (2024)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Szymanowicz, S., Rupprecht, C., Vedaldi, A.: Splatter Image: ultra-fast single-view 3D reconstruction. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Truong, P., Rakotosaona, M.J., Manhardt, F., Tombari, F.: SPARF: neural radiance fields from sparse and noisy poses. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00408"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600\u2013612 (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Wewer, C., Raj, K., Ilg, E., Schiele, B., Lenssen, J.E.: latentSplat: autoencoding variational gaussians for fast generalizable 3D reconstruction. ECCV (2024)","DOI":"10.1007\/978-3-031-73021-4_27"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Wu, R., et\u00a0al.: ReconFusion: 3D reconstruction with diffusion priors. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: MuRF: multi-baseline radiance fields. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01894"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Tao, D.: GMFlow: learning optical flow via global matching. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Unifying flow, stereo and depth estimation. PAMI (2023)","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J.: AANet: adaptive aggregation network for efficient stereo matching. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: PixelNeRF: neural radiance fields from one or few images. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"21_CR47","unstructured":"Yu, Z., Peng, S., Niemeyer, M., Sattler, T., Geiger, A.: MonoSDF: exploring monocular geometric cues for neural implicit surface reconstruction. NeurIPS (2022)"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: GS-LRM: large reconstruction model for 3D gaussian splatting. arXiv (2024)","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"21_CR49","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: GPS-Gaussian: generalizable pixel-wise 3D gaussian splatting for real-time human novel view synthesis. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01861"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. TOG 65, 1\u201312 (2018)","DOI":"10.1145\/3197517.3201323"}],"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\/978-3-031-72664-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T08:28:43Z","timestamp":1732955323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 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"}}]}}