{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:46:32Z","timestamp":1777657592867,"version":"3.51.4"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732225","type":"print"},{"value":"9783031732232","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"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\/978-3-031-73223-2_24","type":"book-chapter","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T18:47:59Z","timestamp":1731005279000},"page":"434-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["NeRF-MAE: Masked AutoEncoders for\u00a0Self-supervised 3D Representation Learning for\u00a0Neural Radiance Fields"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1955-6194","authenticated-orcid":false,"given":"Muhammad Zubair","family":"Irshad","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6231-6137","authenticated-orcid":false,"given":"Sergey","family":"Zakharov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8715-8307","authenticated-orcid":false,"given":"Vitor","family":"Guizilini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8820-550X","authenticated-orcid":false,"given":"Adrien","family":"Gaidon","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2626-2004","authenticated-orcid":false,"given":"Zsolt","family":"Kira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3111-3812","authenticated-orcid":false,"given":"Rares","family":"Ambrus","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"24_CR1","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2Vec: a general framework for self-supervised learning in speech, vision and language. In: International Conference on Machine Learning, pp. 1298\u20131312. PMLR (2022)"},{"key":"24_CR2","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5855\u20135864 (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"24_CR3","unstructured":"Cen, J., et al.: Segment anything in 3D with NeRFs. In: NeurIPS (2023)"},{"key":"24_CR4","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":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: PiMAE: point cloud and image interactive masked autoencoders for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5291\u20135301 (2023)","DOI":"10.1109\/CVPR52729.2023.00512"},{"key":"24_CR6","unstructured":"Chen, W., et al.: Learning to predict 3D objects with an interpolation-based differentiable renderer. In: NeurIPS (2019)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen*, X., Xie*, S., He, K.: An empirical study of training self-supervised vision transformers. arXiv preprint arXiv:2104.02057 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"24_CR8","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":"24_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"24_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"24_CR11","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: a open urban driving simulator. In: CoRL (2017)"},{"key":"24_CR12","unstructured":"Engelmann, F., Manhardt, F., Niemeyer, M., Tateno, K., Marc\u00a0Pollefeys, F.T.: Open-set 3D scene segmentation with rendered novel views. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Fu, H., Cai, B., Gao, L., Zhang, L.X., Wang, J., Li, C., Zeng, Q., Sun, C., Jia, R., Zhao, B., et\u00a0al.: 3d-front: 3d furnished rooms with layouts and semantics. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10933\u201310942 (2021)","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"24_CR14","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_CR15","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al.: UNETR: transformers for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF winter Conference on Applications of Computer Vision, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"He, C., Li, R., Li, S., Zhang, L.: Voxel set transformer: a set-to-set approach to 3D object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arxiv preprint arxiv: 2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Hess, G., Jaxing, J., Svensson, E., Hagerman, D., Petersson, C., Svensson, L.: Masked autoencoders for self-supervised learning on automotive point clouds. arXiv preprint arXiv:2207.00531 (2022)","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Hong, Y., Lin, C., Du, Y., Chen, Z., Tenenbaum, J.B., Gan, C.: 3D concept learning and reasoning from multi-view images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9202\u20139212 (2023)","DOI":"10.1109\/CVPR52729.2023.00888"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., Xie, S.: Exploring data-efficient 3D scene understanding with contrastive scene contexts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15587\u201315597 (2021)","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Hu, B., Huang, J., Liu, Y., Tai, Y.W., Tang, C.K.: NeRF-RPN: a general framework for object detection in NeRFs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23528\u201323538 (2023)","DOI":"10.1109\/CVPR52729.2023.02253"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., Kollar, T., Laskey, M., Stone, K., Kira, Z.: CenterSnap: single-shot multi-object 3D shape reconstruction and categorical 6D pose and size estimation. In: IEEE International Conference on Robotics and Automation (ICRA) (2022)","DOI":"10.1109\/ICRA46639.2022.9811799"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., Zakharov, S., Ambrus, R., Kollar, T., Kira, Z., Gaidon, A.: ShAPO: implicit representations for multi object shape appearance and pose optimization. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20086-1_16"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., et al.: NeO 360: neural fields for sparse view synthesis of outdoor scenes. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00843"},{"key":"24_CR25","first-page":"26105","volume":"35","author":"Y Jeong","year":"2022","unstructured":"Jeong, Y., et al.: PeRFception: perception using radiance fields. Adv. Neural. Inf. Process. Syst. 35, 26105\u201326121 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, L., Yang, Z., Shi, S., Golyanik, V., Dai, D., Schiele, B.: Self-supervised pre-training with masked shape prediction for 3D scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1168\u20131178 (2023)","DOI":"10.1109\/CVPR52729.2023.00119"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: LERF: language embedded radiance fields. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Kuang, Z., Olszewski, K., Chai, M., Huang, Z., Achlioptas, P., Tulyakov, S.: NeROIC: neural rendering of objects from online image collections. arXiv preprint arXiv:2201.02533 (2022)","DOI":"10.1145\/3528223.3530177"},{"key":"24_CR29","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"},{"key":"24_CR30","doi-asserted-by":"publisher","unstructured":"Liang, Y., Zhao, S., Yu, B., Zhang, J., He, F.: MeshMAE: masked autoencoders for 3D mesh data analysis. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13663, pp. 37\u201354. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_3","DOI":"10.1007\/978-3-031-20062-5_3"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Liu, H., Cai, M., Lee, Y.J.: Masked discrimination for self-supervised learning on point clouds. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"24_CR32","unstructured":"Liu, L., Gu, J., Lin, K.Z., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. NeurIPS (2020)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, B., Huang, J., Tai, Y.W., Tang, C.K.: Instance neural radiance field. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 787\u2013796 (2023)","DOI":"10.1109\/ICCV51070.2023.00079"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Manolis Savva*, et al.: Habitat: a platform for embodied AI research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Voxel transformer for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"24_CR37","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"},{"issue":"4","key":"24_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. (ToG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"24_CR39","unstructured":"Nguyen, T.A.Q., Bourki, A., Macudzinski, M., Brunel, A., Bennamoun, M.: Semantically-aware neural radiance fields for visual scene understanding: a comprehensive review. arXiv preprint arXiv:2402.11141 (2024)"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.: Differentiable volumetric rendering: learning implicit 3D representations without 3D supervision. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Oechsle, M., Mescheder, L., Niemeyer, M., Strauss, T., Geiger, A.: Texture fields: learning texture representations in function space. In: Proceedings IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00463"},{"key":"24_CR43","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":"24_CR44","doi-asserted-by":"publisher","unstructured":"Pang, Y., Wang, W., Tay, F.E., Liu, W., Tian, Y., Yuan, L.: Masked autoencoders for point cloud self-supervised learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part II, vol. 13662, pp. 604\u2013621. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_35","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"24_CR46","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"24_CR47","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? Adv. Neural. Inf. Process. Syst. 34, 12116\u201312128 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR48","unstructured":"Ramakrishnan, S.K., et al.: Habitat-Matterport 3D dataset (HM3d): 1000 large-scale 3D environments for embodied AI. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2021)"},{"key":"24_CR49","unstructured":"Remelli, E., et al.: MeshSDF: differentiable Iso-surface extraction. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 22468\u201322478. Curran Associates, Inc. (2020)"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10912\u201310922 (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Roessle, B., Barron, J.T., Mildenhall, B., Srinivasan, P.P., Nie\u00dfner, M.: Dense depth priors for neural radiance fields from sparse input views. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12892\u201312901 (2022)","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"24_CR52","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, 5-9 October 2015, Proceedings, Part III 18, pp. 234\u2013241. Springer (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"24_CR53","doi-asserted-by":"publisher","unstructured":"Rukhovich, D., Vorontsova, A., Konushin, A.: FCAF3D: fully convolutional anchor-free 3d object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13670, pp. 477\u2013493. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_28","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Rukhovich, D., Vorontsova, A., Konushin, A.: ImVoxelNet: image to voxels projection for monocular and multi-view general-purpose 3D object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2397\u20132406 (2022)","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"24_CR55","unstructured":"Shen, W., Yang, G., Yu, A., Wong, J., Kaelbling, L.P., Isola, P.: Distilled feature fields enable few-shot language-guided manipulation. In: 7th Annual Conference on Robot Learning (2023)"},{"key":"24_CR56","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Panoptic lifting for 3D scene understanding with neural fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9043\u20139052 (2023)","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"24_CR57","doi-asserted-by":"crossref","unstructured":"Simeonov, A., et a;l.: Neural descriptor fields: SE(3)-equivariant object representations for manipulation. In: ICRA (2022)","DOI":"10.1109\/ICRA46639.2022.9812146"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Sucar, E., Liu, S., Ortiz, J., Davison, A.J.: iMAP: implicit mapping and positioning in real-time. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6229\u20136238 (2021)","DOI":"10.1109\/ICCV48922.2021.00617"},{"key":"24_CR59","doi-asserted-by":"crossref","unstructured":"Takikawa, T., et al.: Neural geometric level of detail: real-time rendering with implicit 3D shapes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"24_CR60","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":"24_CR61","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Self-supervised pre-training of swin transformers for 3D medical image analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20730\u201320740 (2022)","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"24_CR62","doi-asserted-by":"crossref","unstructured":"Trevithick, A., Yang, B.: GRF: learning a general radiance field for 3D representation and rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15182\u201315192 (2021)","DOI":"10.1109\/ICCV48922.2021.01490"},{"key":"24_CR63","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., Chen, D., Liao, J.: CLIP-NeRF: text-and-image driven manipulation of neural radiance fields (2022)","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"24_CR64","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":"24_CR65","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (TOG) 38, 1\u201312 (2019)","DOI":"10.1145\/3326362"},{"key":"24_CR66","unstructured":"Wang, Z., Wu, S., Xie, W., Chen, M., Prisacariu, V.A.: NeRF$$--$$: Neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064 (2021)"},{"key":"24_CR67","first-page":"3502","volume":"35","author":"P Weinzaepfel","year":"2022","unstructured":"Weinzaepfel, P., et al.: CroCo: self-supervised pre-training for 3D vision tasks by cross-view completion. Adv. Neural. Inf. Process. Syst. 35, 3502\u20133516 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR68","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: ReconFusion: 3D reconstruction with diffusion priors. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"24_CR69","unstructured":"Xie, Y., et al.: Neural fields in visual computing and beyond (2021)"},{"key":"24_CR70","unstructured":"Xie, Z., et al.: Self-supervised learning with swin transformers. arXiv preprint arXiv:2105.04553 (2021)"},{"key":"24_CR71","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"24_CR72","doi-asserted-by":"crossref","unstructured":"Xu, C., et\u00a0al.: NeRF-Det: learning geometry-aware volumetric representation for multi-view 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23320\u201323330 (2023)","DOI":"10.1109\/ICCV51070.2023.02131"},{"key":"24_CR73","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Implicit autoencoder for point cloud self-supervised representation learning. arXiv preprint arXiv:2201.00785 (2022)","DOI":"10.1109\/ICCV51070.2023.01336"},{"key":"24_CR74","doi-asserted-by":"crossref","unstructured":"Yan, X., Lin, L., Mitra, N.J., Lischinski, D., Cohen-Or, D., Huang, H.: ShapeFormer: transformer-based shape completion via sparse representation (2022)","DOI":"10.1109\/CVPR52688.2022.00614"},{"key":"24_CR75","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Learning object-compositional neural radiance field for editable scene rendering. In: International Conference on Computer Vision (ICCV) (October 2021)","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"24_CR76","unstructured":"Yang, Y.Q., Guo, Y.X., Xiong, J.Y., Liu, Y., Pan, H., Wang, P.S., Tong, X., Guo, B.: Swin3D: a pretrained transformer backbone for 3d indoor scene understanding (2023)"},{"key":"24_CR77","doi-asserted-by":"crossref","unstructured":"Yariv, L., et al.: BakedSDF: Meshing neural SDFs for real-time view synthesis (2023)","DOI":"10.1145\/3588432.3591536"},{"key":"24_CR78","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: Segment and edit anything in 3D scenes. arXiv preprint arXiv:2312.00732 (2023)","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"24_CR79","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Lin, T.Y., Rodriguez, A., Isola, P.: NeRF-supervision: Learning dense object descriptors from neural radiance fields. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 6496\u20136503. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812291"},{"key":"24_CR80","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Lin, T.Y., Rodriguez, A., Isola, P.: NeRF-Supervision: learning dense object descriptors from neural radiance fields. In: IEEE Conference on Robotics and Automation (ICRA) (2022)","DOI":"10.1109\/ICRA46639.2022.9812291"},{"key":"24_CR81","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 (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"24_CR82","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":"24_CR83","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., Lu, J.: Point-BERT: Pre-training 3D point cloud transformers with masked point modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19313\u201319322 (2022)","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"24_CR84","doi-asserted-by":"crossref","unstructured":"Yuan, W., Lv, Z., Schmidt, T., Lovegrove, S.: STaR: self-supervised tracking and reconstruction of rigid objects in motion with neural rendering. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01294"},{"key":"24_CR85","unstructured":"Ze, Y., et al.: Multi-task real robot learning with generalizable neural feature fields. In: CoRL (2023)"},{"key":"24_CR86","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12104\u201312113 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"24_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cui, Z., Zhang, Y., Zeng, B., Pollefeys, M., Liu, S.: Holistic 3D scene understanding from a single image with implicit representation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"24_CR88","unstructured":"Zhang, R., et al.: Point-M2AE: multi-scale masked autoencoders for hierarchical point cloud pre-training. arXiv preprint arXiv:2205.14401 (2022)"},{"key":"24_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, L., Qiao, Y., Gao, P., Li, H.: Learning 3D representations from 2D pre-trained models via image-to-point masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21769\u201321780 (2023)","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"24_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud (2021)","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"24_CR91","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.: In-place scene labelling and understanding with implicit scene representation. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"24_CR92","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\/978-3-031-73223-2_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:07:50Z","timestamp":1731006470000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73223-2_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"ISBN":["9783031732225","9783031732232"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73223-2_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,8]]},"assertion":[{"value":"8 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"}}]}}