{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T03:23:24Z","timestamp":1783567404570,"version":"3.55.0"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198267","type":"print"},{"value":"9783031198274","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19827-4_1","type":"book-chapter","created":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T14:42:19Z","timestamp":1667313739000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":86,"title":["SimpleRecon: 3D Reconstruction Without 3D Convolutions"],"prefix":"10.1007","author":[{"given":"Mohamed","family":"Sayed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Gibson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamie","family":"Watson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor","family":"Prisacariu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Firman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cl\u00e9ment","family":"Godard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,2]]},"reference":[{"key":"1_CR1","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: CVPR (2021)"},{"key":"1_CR2","unstructured":"Bozic, A., Palafox, P., Thies, J., Dai, A., Nie\u00dfner, M.: TransformerFusion: monocular RGB scene reconstruction using transformers. In: NeurIPS (2021)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00567"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Schmid, C., Sminchisescu, C.: Self-supervised learning with geometric constraints in monocular video: Connecting flow, depth, and camera. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00716"},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.1109\/TPAMI.2019.2947374","volume":"42","author":"X Cheng","year":"2019","unstructured":"Cheng, X., Wang, P., Yang, R.: Learning depth with convolutional spatial propagation network. PAMI 42, 2361\u20132379 (2019)","journal-title":"PAMI"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Choe, J., Im, S., Rameau, F., Kang, M., Kweon, I.S.: VolumeFusion: deep depth fusion for 3D scene reconstruction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01578"},{"key":"1_CR8","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":"1_CR9","doi-asserted-by":"crossref","unstructured":"Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques (1996)","DOI":"10.1145\/237170.237269"},{"key":"1_CR10","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Drory, A., Haubold, C., Avidan, S., Hamprecht, F.: Semi-global matching: a principled derivation in terms of message passing. In: German Conference on Pattern Recognition (2014)","DOI":"10.1007\/978-3-319-11752-2_4"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Duzceker, A., Galliani, S., Vogel, C., Speciale, P., Dusmanu, M., Pollefeys, M.: Deepvideomvs: multi-view stereo on video with recurrent spatio-temporal fusion. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01507"},{"key":"1_CR13","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NeurIPS (2014)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Facil, J.M., Ummenhofer, B., Zhou, H., Montesano, L., Brox, T., Civera, J.: CAM-Convs: camera-aware multi-scale convolutions for single-view depth. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01210"},{"key":"1_CR15","unstructured":"Falcon, W., et al.: Pytorch lightning. GitHub. Note: https:\/\/github.com\/PyTorchLightning\/pytorch-lightning (2019)"},{"key":"1_CR16","unstructured":"Fischer, P., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)"},{"key":"1_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0600000052","volume":"9","author":"Y Furukawa","year":"2015","unstructured":"Furukawa, Y., Hern\u00e1ndez, C.: Multi-view stereo: a tutorial. Found. Trends Comput. Graphics Vis. 9, 1\u2013148 (2015)","journal-title":"Found. Trends Comput. Graphics Vis."},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Glocker, B., Izadi, S., Shotton, J., Criminisi, A.: Real-time RGB-D camera relocalization. In: International Symposium on Mixed and Augmented Reality (ISMAR). IEEE, October 2013","DOI":"10.1109\/ISMAR.2013.6671777"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR22","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2007","unstructured":"Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. PAMI 30, 328\u2013341 (2007)","journal-title":"PAMI"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Hou, Y., Kannala, J., Solin, A.: Multi-view stereo by temporal nonparametric fusion. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00274"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Hu, J., Ozay, M., Zhang, Y., Okatani, T.: Revisiting single image depth estimation: toward higher resolution maps with accurate object boundaries. In: WACV (2018)","DOI":"10.1109\/WACV.2019.00116"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: DeepMVS: learning multi-view stereopsis. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00298"},{"key":"1_CR26","unstructured":"Im, S., Jeon, H.G., Lin, S., Kweon, I.S.: DPSNet: end-to-end deep plane sweep stereo. ICLR (2019)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L.: SurfaceNet: an end-to-end 3D neural network for multiview stereopsis. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.253"},{"issue":"1","key":"1_CR28","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1109\/LRA.2015.2512958","volume":"1","author":"O K\u00e4hler","year":"2015","unstructured":"K\u00e4hler, O., Prisacariu, V., Valentin, J., Murray, D.: Hierarchical voxel block hashing for efficient integration of depth images. IEEE Robot. Autom. Lett. 1(1), 192\u2013197 (2015)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1_CR29","unstructured":"Kang, S.B., Szeliski, R., Chai, J.: Handling occlusions in dense multi-view stereo. In: CVPR (2001)"},{"key":"1_CR30","unstructured":"Kar, A., H\u00e4ne, C., Malik, J.: Learning a multi-view stereo machine. In: NeurIPS (2017)"},{"key":"1_CR31","unstructured":"Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Eurographics. SGP 2006, Eurographics Association (2006)"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Kendall, A., et al.: End-to-end learning of geometry and context for deep stereo regression. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.17"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Kuznietsov, Y., Proesmans, M., Van Gool, L.: CoMoDA: continuous monocular depth adaptation using past experiences. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00295"},{"issue":"3","key":"1_CR34","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/BF00977785","volume":"9","author":"DT Lee","year":"1980","unstructured":"Lee, D.T., Schachter, B.J.: Two algorithms for constructing a delaunay triangulation. Int. J. Comput. Inf. Sci. 9(3), 219\u2013242 (1980)","journal-title":"Int. J. Comput. Inf. Sci."},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Liang, Z., et al.: Learning for disparity estimation through feature constancy. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00297"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Long, X., Liu, L., Li, W., Theobalt, C., Wang, W.: Multi-view depth estimation using epipolar spatio-temporal networks. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00816"},{"key":"1_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1007\/978-3-030-58545-7_37","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Long","year":"2020","unstructured":"Long, X., Liu, L., Theobalt, C., Wang, W.: Occlusion-aware depth estimation with adaptive normal constraints. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 640\u2013657. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_37"},{"key":"1_CR40","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1145\/37402.37422","volume":"21","author":"WE Lorensen","year":"1987","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. ACM SIGGRAPH Comput. Graphics 21, 163\u2013169 (1987)","journal-title":"ACM SIGGRAPH Comput. Graphics"},{"key":"1_CR41","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Luo, X., Huang, J.B., Szeliski, R., Matzen, K., Kopf, J.: Consistent video depth estimation. In: ACM SIGGRAPH (2020)","DOI":"10.1145\/3386569.3392377"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Marcel, S., Rodriguez, Y.: Torchvision the machine-vision package of torch. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1485\u20131488 (2010)","DOI":"10.1145\/1873951.1874254"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"1_CR45","unstructured":"McCraith, R., Neumann, L., Zisserman, A., Vedaldi, A.: Monocular depth estimation with self-supervised instance adaptation. arXiv:2004.05821 (2020)"},{"key":"1_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1007\/978-3-030-58571-6_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Murez","year":"2020","unstructured":"Murez, Z., van As, T., Bartolozzi, J., Sinha, A., Badrinarayanan, V., Rabinovich, A.: Atlas: End-to-End 3D scene reconstruction from posed images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 414\u2013431. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_25"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Izadi, S., Hilliges, O.: KinectFusion: real-time dense surface mapping and tracking. In: UIST (2011)","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Lovegrove, S.J., Davison, A.J.: DTAM: dense tracking and mapping in real-time. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"1_CR49","first-page":"1","volume":"32","author":"M Nie\u00dfner","year":"2013","unstructured":"Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Stamminger, M.: Real-time 3D reconstruction at scale using voxel hashing. ACM Trans. Graphics (ToG) 32, 1\u201311 (2013)","journal-title":"ACM Trans. Graphics (ToG)"},{"key":"1_CR50","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"1_CR51","doi-asserted-by":"publisher","first-page":"6813","DOI":"10.1109\/LRA.2020.3017478","volume":"5","author":"V Patil","year":"2020","unstructured":"Patil, V., Van Gansbeke, W., Dai, D., Van Gool, L.: Don\u2019t forget the past: recurrent depth estimation from monocular video. IEEE Robot. Autom. Lett. 5, 6813\u20136820 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1_CR52","unstructured":"Prisacariu, V.A., et al.: Infinitam v3: a framework for large-scale 3D reconstruction with loop closure. arXiv preprint arXiv:1708.00783 (2017)"},{"key":"1_CR53","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. PAMI 44, 1623\u20131637 (2020)","journal-title":"PAMI"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Rich, A., Stier, N., Sen, P., H\u00f6llerer, T.: 3dvnet: multi-view depth prediction and volumetric refinement. In: International Conference on 3D Vision (3DV) (2021)","DOI":"10.1109\/3DV53792.2021.00079"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Runz, M., Buffier, M., Agapito, L.: MaskFusion: real-time recognition, tracking and reconstruction of multiple moving objects. In: ISMAR (2018)","DOI":"10.1109\/ISMAR.2018.00024"},{"key":"1_CR56","unstructured":"Scharstein, D., Szeliski, R., Zabih, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. In: IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001) (2001)"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"1_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"JL Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501\u2013518. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Scona, R., Jaimez, M., Petillot, Y.R., Fallon, M., Cremers, D.: StaticFusion: background reconstruction for dense RGB-D SLAM in dynamic environments. In: ICRA (2018)","DOI":"10.1109\/ICRA.2018.8460681"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.377"},{"key":"1_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/978-3-030-58529-7_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Shu","year":"2020","unstructured":"Shu, C., Yu, K., Duan, Z., Yang, K.: Feature-metric loss for self-supervised learning of depth and egomotion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 572\u2013588. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_34"},{"key":"1_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58589-1_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Sinha","year":"2020","unstructured":"Sinha, A., Murez, Z., Bartolozzi, J., Badrinarayanan, V., Rabinovich, A.: DELTAS: depth estimation by learning triangulation and densification of sparse points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 104\u2013121. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_7"},{"key":"1_CR63","doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., Nie\u00dfner, M., Wetzstein, G., Zollh\u00f6fer, M.: DeepVoxels: learning persistent 3D feature embeddings. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00254"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Stier, N., Rich, A., Sen, P., H\u00f6llerer, T.: Vortx: volumetric 3D reconstruction with transformers for voxelwise view selection and fusion. In: International Conference on 3D Vision (3DV) (2021)","DOI":"10.1109\/3DV53792.2021.00042"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Sun, J., Xie, Y., Chen, L., Zhou, X., Bao, H.: NeuralRecon: real-time coherent 3D reconstruction from monocular video. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"1_CR66","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: Mnasnet: platform-aware neural architecture search for mobile. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"1_CR67","unstructured":"Tan, M., Le, Q.: Efficientnetv2: Smaller models and faster training. In: ICML (2021)"},{"key":"1_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-030-11015-4_52","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"D Tananaev","year":"2019","unstructured":"Tananaev, D., Zhou, H., Ummenhofer, B., Brox, T.: Temporally consistent depth estimation in videos with recurrent architectures. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 689\u2013701. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11015-4_52"},{"key":"1_CR69","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Wang, K., Shen, S.: MVDepthNet: real-time multiview depth estimation neural network. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00037"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Watson, J., Aodha, O.M., Prisacariu, V., Brostow, G., Firman, M.: The temporal opportunist: self-supervised multi-frame monocular depth. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"1_CR72","doi-asserted-by":"crossref","unstructured":"Watson, J., Firman, M., Brostow, G.J., Turmukhambetov, D.: Self-supervised monocular depth hints. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00225"},{"key":"1_CR73","unstructured":"Whelan, T., Kaess, M., Fallon, M., Johannsson, H., Leonard, J., McDonald, J.: Kintinuous: spatially extended KinectFusion. In: RSS Workshop on RGB-D: Advanced Reasoning with Depth Camera (2012)"},{"key":"1_CR74","doi-asserted-by":"crossref","unstructured":"Whelan, T., Leutenegger, S., Salas-Moreno, R., Glocker, B., Davison, A.: ElasticFusion: dense SLAM without a pose graph. In: Robotics: Science and Systems (2015)","DOI":"10.15607\/RSS.2015.XI.001"},{"key":"1_CR75","doi-asserted-by":"publisher","unstructured":"Wightman, R.: Pytorch image models. https:\/\/github.com\/rwightman\/pytorch-image-models (2019). https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"1_CR76","doi-asserted-by":"crossref","unstructured":"Wimbauer, F., Yang, N., von Stumberg, L., Zeller, N., Cremers, D.: MonoRec: semi-supervised dense reconstruction in dynamic environments from a single moving camera. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00605"},{"key":"1_CR77","doi-asserted-by":"publisher","first-page":"3446","DOI":"10.1109\/TVCG.2020.3023634","volume":"26","author":"X Yang","year":"2020","unstructured":"Yang, X., et al.: Mobile3DRecon: real-time monocular 3D reconstruction on a mobile phone. IEEE Trans. Visual. Comput. Graphics 26, 3446\u20133456 (2020)","journal-title":"IEEE Trans. Visual. Comput. Graphics"},{"key":"1_CR78","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1007\/978-3-030-01237-3_47","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Yao","year":"2018","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 785\u2013801. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_47"},{"key":"1_CR79","doi-asserted-by":"crossref","unstructured":"Yee, K., Chakrabarti, A.: Fast deep stereo with 2D convolutional processing of cost signatures. In: WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093273"},{"key":"1_CR80","doi-asserted-by":"crossref","unstructured":"Yin, W., Liu, Y., Shen, C., Yan, Y.: Enforcing geometric constraints of virtual normal for depth prediction. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00578"},{"key":"1_CR81","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Learning to recover 3D scene shape from a single image. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"1_CR82","first-page":"2287","volume":"17","author":"J \u017dbontar","year":"2016","unstructured":"\u017dbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. JMLR 17, 2287\u20132318 (2016)","journal-title":"JMLR"},{"key":"1_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, F., Prisacariu, V., Yang, R., Torr, P.H.: GA-Net: guided aggregation net for end-to-end stereo matching. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00027"},{"key":"1_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-030-58536-5_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Zhang","year":"2020","unstructured":"Zhang, F., Qi, X., Yang, R., Prisacariu, V., Wah, B., Torr, P.: Domain-invariant stereo matching networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 420\u2013439. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_25"},{"key":"1_CR85","doi-asserted-by":"crossref","unstructured":"Zhao, W., Liu, S., Wei, Y., Guo, H., Liu, Y.J.: A confidence-based iterative solver of depths and surface normals for deep multi-view stereo. In: ICCV, pp. 6168\u20136177, October 2021","DOI":"10.1109\/ICCV48922.2021.00611"},{"key":"1_CR86","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Kong, S., Fowlkes, C.: Camera pose matters: improving depth prediction by mitigating pose distribution bias. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01550"},{"key":"1_CR87","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., Liang, J.: UNet++: a nested U-Net architecture for medical image segmentation. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (2018)","DOI":"10.1007\/978-3-030-00889-5_1"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19827-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T14:42:57Z","timestamp":1667313777000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19827-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198267","9783031198274"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19827-4_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"2 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}