{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T01:01:17Z","timestamp":1778115677557,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732089","type":"print"},{"value":"9783031732096","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73209-6_19","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"325-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["GGRt: Towards Pose-Free Generalizable 3D Gaussian Splatting in\u00a0Real-Time"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2419-2700","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"first","affiliation":[]},{"given":"Yuanyuan","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8012-1547","authenticated-orcid":false,"given":"Chenming","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Dingwen","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yalun","family":"Dai","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Haocheng","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Errui","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Junwei","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Bian, W., Wang, Z., Li, K., Bian, J.W., Prisacariu, V.A.: NoPe-NeRF: optimising neural radiance field with no pose prior. In: CVPR, pp. 4160\u20134169 (2023)","DOI":"10.1109\/CVPR52729.2023.00405"},{"key":"19_CR2","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":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Lee, G.H.: DBARF: deep bundle-adjusting generalizable neural radiance fields. In: CVPR, pp. 24\u201334 (2023)","DOI":"10.1109\/CVPR52729.2023.00011"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Duan, F., Yu, J., Chen, L.: T-CorresNet: template guided 3D point cloud completion with correspondence pooling query generation strategy. arXiv preprint arXiv:2407.05008 (2024)","DOI":"10.1007\/978-3-031-72907-2_6"},{"key":"19_CR5","unstructured":"Fu, Y., et al.: 3D reconstruction with generalizable neural fields using scene priors. In: ICLR (2024)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Fu, Y., Liu, S., Kulkarni, A., Kautz, J., Efros, A.A., Wang, X.: COLMAP-free 3D gaussian splatting. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01965"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"issue":"5","key":"19_CR9","doi-asserted-by":"publisher","first-page":"2844","DOI":"10.1109\/LRA.2023.3260724","volume":"8","author":"X Gu","year":"2023","unstructured":"Gu, X., Yuan, W., Dai, Z., Tang, C., Zhu, S., Tan, P.: DRO: deep recurrent optimizer for video to depth. IEEE Robot. Autom. Lett. 8(5), 2844\u20132851 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Hong, S., Jung, J., Shin, H., Yang, J., Kim, S., Luo, C.: Unifying correspondence, pose and nerf for pose-free novel view synthesis from stereo pairs. arXiv preprint arXiv:2312.07246 (2023)","DOI":"10.1109\/CVPR52733.2024.01909"},{"key":"19_CR11","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. In: ICLR (2024)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Jiao, Y., et al.: Instance-aware multi-camera 3D object detection with structural priors mining and self-boosting learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 2598\u20132606 (2024)","DOI":"10.1609\/aaai.v38i3.28037"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM TOG 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Lai, Z., Liu, S., Efros, A.A., Wang, X.: Video autoencoder: self-supervised disentanglement of static 3d structure and motion. In: ICCV, pp. 9730\u20139740 (2021)","DOI":"10.1109\/ICCV48922.2021.00959"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: VDG: vision-only dynamic gaussian for driving simulation. arXiv preprint arXiv:2406.18198 (2024)","DOI":"10.1109\/LRA.2025.3555938"},{"key":"19_CR16","unstructured":"Li, H., et al.: XLD: a cross-lane dataset for benchmarking novel driving view synthesis. arXiv preprint arXiv:2406.18360 (2024)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, D., Dai, Y., Liu, N., Cheng, L., Li, J., Wang, J., Han, J.: GP-NeRF: generalized perception nerf for context-aware 3D scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21708\u201321718 (2024)","DOI":"10.1109\/CVPR52733.2024.02051"},{"key":"19_CR18","unstructured":"Li, J., et al.: Instant3D: fast text-to-3D with sparse-view generation and large reconstruction model. In: ICLR (2024)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, L., Wang, Z., Mu, T., He, J.: LoopGaussian: creating 3D cinemagraph with multi-view images via Eulerian motion field. arXiv preprint arXiv:2404.08966 (2024)","DOI":"10.1145\/3664647.3681025"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: BARF: bundle-adjusting neural radiance fields. In: ICCV, pp. 5741\u20135751 (2021)","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Neural rays for occlusion-aware image-based rendering. In: CVPR, pp. 7824\u20137833 (2022)","DOI":"10.1109\/CVPR52688.2022.00767"},{"key":"19_CR22","unstructured":"Liu, Z., et al.: InFusion: inpainting 3D gaussians via learning depth completion from diffusion prior. arXiv preprint arXiv:2404.11613 (2024)"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Meuleman, A., et al.: Progressively optimized local radiance fields for robust view synthesis. In: CVPR, pp. 16539\u201316548 (2023)","DOI":"10.1109\/CVPR52729.2023.01587"},{"issue":"4","key":"19_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322980","volume":"38","author":"B Mildenhall","year":"2019","unstructured":"Mildenhall, B., et al.: Local light field fusion: practical view synthesis with prescriptive sampling guidelines. ACM TOG 38(4), 1\u201314 (2019)","journal-title":"ACM TOG"},{"issue":"1","key":"19_CR25","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":"19_CR26","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S.M., et al.: Scene representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., et al.: RUST: latent neural scene representations from unposed imagery. In: CVPR, pp. 17297\u201317306 (2023)","DOI":"10.1109\/CVPR52729.2023.01659"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., et\u00a0al.: Scene representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6229\u20136238 (2022)","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"19_CR29","first-page":"19313","volume":"34","author":"V Sitzmann","year":"2021","unstructured":"Sitzmann, V., Rezchikov, S., Freeman, B., Tenenbaum, J., Durand, F.: Light field networks: neural scene representations with single-evaluation rendering. Adv. Neural. Inf. Process. Syst. 34, 19313\u201319325 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR30","unstructured":"Smith, C., Du, Y., Tewari, A., Sitzmann, V.: FlowCam: training generalizable 3d radiance fields without camera poses via pixel-aligned scene flow. In: NeurIPS (2023)"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Suhail, M., Esteves, C., Sigal, L., Makadia, A.: Light field neural rendering. In: CVPR, pp. 8269\u20138279 (2022)","DOI":"10.1109\/CVPR52688.2022.00809"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"19_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Tian, F., Du, S., Duan, Y.: MonoNeRF: learning a generalizable dynamic radiance field from monocular videos. In: ICCV, pp. 17903\u201317913 (2023)","DOI":"10.1109\/ICCV51070.2023.01641"},{"key":"19_CR35","unstructured":"Wang, P., Chen, X., Chen, T., Venugopalan, S., Wang, Z., et\u00a0al.: Is attention all nerf needs? In: ICLR (2023)"},{"key":"19_CR36","unstructured":"Wang, P., et al.: PF-LRM: pose-free large reconstruction model for joint pose and shape prediction. In: ICLR (2024)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: CVPR, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"issue":"4","key":"19_CR38","first-page":"600","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 TIP 13(4), 600\u2013612 (2004)","journal-title":"IEEE TIP"},{"key":"19_CR39","unstructured":"Wang, Z., Wu, S., Xie, W., Chen, M., Prisacariu, V.A.: Nerf\u2013: neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064 (2021)"},{"key":"19_CR40","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, pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: iNeRF: inverting neural radiance fields for pose estimation. In: IROS, pp. 1323\u20131330. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: neural radiance fields from one or few images. In: CVPR, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"19_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/978-3-031-19821-2_41","volume-title":"Computer Vision \u2013 ECCV 2022","author":"K Zhang","year":"2022","unstructured":"Zhang, K., et al.: ARF: artistic radiance fields. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 717\u2013733. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_41"},{"key":"19_CR44","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, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"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\/978-3-031-73209-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T12:22:53Z","timestamp":1744114973000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73209-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732089","9783031732096"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73209-6_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}