{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:25:55Z","timestamp":1777656355997,"version":"3.51.4"},"publisher-location":"Cham","reference-count":86,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730382","type":"print"},{"value":"9783031730399","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73039-9_16","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"274-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["AugUndo: Scaling Up Augmentations for\u00a0Monocular Depth Completion and\u00a0Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6260-9693","authenticated-orcid":false,"given":"Yangchao","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4834-051X","authenticated-orcid":false,"given":"Tian Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0787-2082","authenticated-orcid":false,"given":"Hyoungseob","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2902-6362","authenticated-orcid":false,"given":"Stefano","family":"Soatto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9308-7085","authenticated-orcid":false,"given":"Dong","family":"Lao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3157-6016","authenticated-orcid":false,"given":"Alex","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"16_CR1","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7063\u20137072 (2019)","DOI":"10.1109\/ICCV.2019.00716"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, X., Wang, P., Guan, C., Yang, R.: CSPN++: learning context and resource aware convolutional spatial propagation networks for depth completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 10615\u201310622 (2020)","DOI":"10.1609\/aaai.v34i07.6635"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-01270-0_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Cheng","year":"2018","unstructured":"Cheng, X., Wang, P., Yang, R.: Depth estimation via affinity learned with convolutional spatial propagation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 108\u2013125. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_7"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Choi, H., et al.: Adaptive confidence thresholding for monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12808\u201312818 (2021)","DOI":"10.1109\/ICCV48922.2021.01257"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: Richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference On Computer Visio, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"16_CR7","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Eldesokey, A., Felsberg, M., Holmquist, K., Persson, M.: Uncertainty-aware CNNs for depth completion: uncertainty from beginning to end. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12014\u201312023 (2020)","DOI":"10.1109\/CVPR42600.2020.01203"},{"key":"16_CR9","unstructured":"Ezhov, V., et al.: All-day depth completion. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2024)"},{"issue":"2","key":"16_CR10","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1109\/LRA.2019.2896963","volume":"4","author":"X Fei","year":"2019","unstructured":"Fei, X., Wong, A., Soatto, S.: Geo-supervised visual depth prediction. IEEE Robot. Autom. Lett. 4(2), 1661\u20131668 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"6","key":"16_CR11","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"16_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-46484-8_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Garg","year":"2016","unstructured":"Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VIII. LNCS, vol. 9912, pp. 740\u2013756. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The Kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"16_CR15","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"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3D packing for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2485\u20132494 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"16_CR17","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. In: International Conference on Learning Representations (2019)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Hu, M., Wang, S., Li, B., Ning, S., Fan, L., Gong, X.: PENet: towards precise and efficient image guided depth completion. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13656\u201313662. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561035"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Jaritz, M., De\u00a0Charette, R., Wirbel, E., Perrotton, X., Nashashibi, F.: Sparse and dense data with CNNs: depth completion and semantic segmentation. In: 2018 International Conference on 3D Vision (3DV), pp. 52\u201360. IEEE (2018)","DOI":"10.1109\/3DV.2018.00017"},{"issue":"3","key":"16_CR20","doi-asserted-by":"publisher","first-page":"6391","DOI":"10.1109\/LRA.2022.3171727","volume":"7","author":"J Jeon","year":"2022","unstructured":"Jeon, J., Lim, H., Seo, D.U., Myung, H.: Struct-MDC: mesh-refined unsupervised depth completion leveraging structural regularities from visual slam. IEEE Robot. Autom. Lett. 7(3), 6391\u20136398 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"16_CR21","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/978-3-031-20086-1_15","volume-title":"ECCV 2022","author":"J Kam","year":"2022","unstructured":"Kam, J., Kim, J., Kim, S., Park, J., Lee, S.: CostDCNet: cost volume based depth completion for a single RGB-D image. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 257\u2013274. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_15"},{"key":"16_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/978-3-030-58565-5_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Klingner","year":"2020","unstructured":"Klingner, M., Term\u00f6hlen, J.-A., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XX. LNCS, vol. 12365, pp. 582\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_35"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Krishna, S., Vandrotti, B.S.: DeepSmooth: efficient and smooth depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3357\u20133366 (2023)","DOI":"10.1109\/CVPRW59228.2023.00338"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Kumar, V.R., Klingner, M., Yogamani, S., Milz, S., Fingscheidt, T., Mader, P.: SynDistNet: self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 61\u201371 (2021)","DOI":"10.1109\/WACV48630.2021.00011"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 239\u2013248. IEEE (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"16_CR26","unstructured":"Lao, D., Wu, Y., Liu, T.Y., Wong, A., Soatto, S.: Sub-token VIT embedding via stochastic resonance transformers. In: International Conference on Machine Learning. PMLR (2024)"},{"key":"16_CR27","unstructured":"Lao, D., Yang, F., Wang, D., Park, H., Lu, S., Wong, A., Soatto, S.: On the viability of monocular depth pre-training for semantic segmentation. In: European Conference on Computer Vision. Springer (2024)"},{"issue":"2","key":"16_CR28","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"V Lepetit","year":"2009","unstructured":"Lepetit, V., Moreno-Noguer, F., Fua, P.: EPNP: an accurate O (N) solution to the PNP problem. Int. J. Comput. Vision 81(2), 155 (2009)","journal-title":"Int. J. Comput. Vision"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Li, A., Yuan, Z., Ling, Y., Chi, W., Zhang, C., et\u00a0al.: A multi-scale guided cascade hourglass network for depth completion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 32\u201340 (2020)","DOI":"10.1109\/WACV45572.2020.9093407"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Li, B., Shen, C., Dai, Y., Van Den\u00a0Hengel, A., He, M.: Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1119\u20131127 (2015)","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Lin, Y., Cheng, T., Zhong, Q., Zhou, W., Yang, H.: Dynamic spatial propagation network for depth completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1638\u20131646 (2022)","DOI":"10.1609\/aaai.v36i2.20055"},{"issue":"10","key":"16_CR32","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2015","unstructured":"Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024\u20132039 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-031-20086-1_3","volume-title":"ECCV 2022, Part II","author":"TY Liu","year":"2022","unstructured":"Liu, T.Y., Agrawal, P., Chen, A., Hong, B.W., Wong, A.: Monitored distillation for positive congruent depth completion. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part II. LNCS, vol. 13662, pp. 35\u201353. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_3"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Lopez-Rodriguez, A., Busam, B., Mikolajczyk, K.: Project to adapt: domain adaptation for depth completion from noisy and sparse sensor data. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69525-5_20"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Lyu, X., et al.: HR-depth: high resolution self-supervised monocular depth estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 2294\u20132301 (2021)","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Ma, F., Cavalheiro, G.V., Karaman, S.: Self-supervised sparse-to-dense: self-supervised depth completion from lidar and monocular camera. In: International Conference on Robotics and Automation (ICRA), pp. 3288\u20133295. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793637"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3d geometric constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5667\u20135675 (2018)","DOI":"10.1109\/CVPR.2018.00594"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Park, H., Gupta, A., Wong, A.: Test-time adaptation for depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20519\u201320529 (2024)","DOI":"10.1109\/CVPR52733.2024.01939"},{"key":"16_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/978-3-030-58601-0_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Park","year":"2020","unstructured":"Park, J., Joo, K., Hu, Z., Liu, C.-K., So Kweon, I.: Non-local spatial propagation network for depth completion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 120\u2013136. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_8"},{"key":"16_CR40","unstructured":"Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621 (2017)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: On the uncertainty of self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3227\u20133237 (2020)","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Poggi, M., Tosi, F., Mattoccia, S.: Learning monocular depth estimation with unsupervised trinocular assumptions. In: 2018 International Conference on 3D Vision (3DV), pp. 324\u2013333. IEEE (2018)","DOI":"10.1109\/3DV.2018.00045"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Qiu, J., et al.: DeepLiDAR: deep surface normal guided depth prediction for outdoor scene from sparse lidar data and single color image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3313\u20133322 (2019)","DOI":"10.1109\/CVPR.2019.00343"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Qu, C., Liu, W., Taylor, C.J.: Bayesian deep basis fitting for depth completion with uncertainty. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16147\u201316157 (2021)","DOI":"10.1109\/ICCV48922.2021.01584"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Qu, C., Nguyen, T., Taylor, C.: Depth completion via deep basis fitting. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 71\u201380 (2020)","DOI":"10.1109\/WACV45572.2020.9093349"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"16_CR47","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Ranjan, A., et al.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12240\u201312249 (2019)","DOI":"10.1109\/CVPR.2019.01252"},{"issue":"5","key":"16_CR49","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2008","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Shivakumar, S.S., Nguyen, T., Miller, I.D., Chen, S.W., Kumar, V., Taylor, C.J.: DFuseNet: deep fusion of RGB and sparse depth information for image guided dense depth completion. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 13\u201320. IEEE (2019)","DOI":"10.1109\/ITSC.2019.8917294"},{"issue":"1","key":"16_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1\u201348 (2019)","journal-title":"J. Big Data"},{"key":"16_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Singh, A.D., et al.: Depth estimation from camera image and mmWave radar point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9275\u20139285 (2023)","DOI":"10.1109\/CVPR52729.2023.00895"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Taylor, L., Nitschke, G.: Improving deep learning with generic data augmentation. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1542\u20131547. IEEE (2018)","DOI":"10.1109\/SSCI.2018.8628742"},{"key":"16_CR56","doi-asserted-by":"crossref","unstructured":"Tosi, F., Aleotti, F., Poggi, M., Mattoccia, S.: Learning monocular depth estimation infusing traditional stereo knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9799\u20139809 (2019)","DOI":"10.1109\/CVPR.2019.01003"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant CNNs. In: 2017 International Conference on 3D Vision (3DV), pp. 11\u201320. IEEE (2017)","DOI":"10.1109\/3DV.2017.00012"},{"issue":"6","key":"16_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618389","volume":"42","author":"R Upadhyay","year":"2023","unstructured":"Upadhyay, R., et al.: Enhancing diffusion models with 3D perspective geometry constraints. ACM Trans. Graph. (TOG) 42(6), 1\u201315 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR59","doi-asserted-by":"crossref","unstructured":"Van\u00a0Gansbeke, W., Neven, D., De\u00a0Brabandere, B., Van\u00a0Gool, L.: Sparse and noisy lidar completion with RGB guidance and uncertainty. In: 2019 16th International Conference on Machine Vision Applications (MVA), pp.\u00a01\u20136. IEEE (2019)","DOI":"10.23919\/MVA.2019.8757939"},{"key":"16_CR60","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2022\u20132030 (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"key":"16_CR61","doi-asserted-by":"crossref","unstructured":"Watson, J., Firman, M., Brostow, G.J., Turmukhambetov, D.: Self-supervised monocular depth hints. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2162\u20132171 (2019)","DOI":"10.1109\/ICCV.2019.00225"},{"key":"16_CR62","first-page":"8486","volume":"33","author":"A Wong","year":"2020","unstructured":"Wong, A., Cicek, S., Soatto, S.: Targeted adversarial perturbations for monocular depth prediction. Adv. Neural. Inf. Process. Syst. 33, 8486\u20138497 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"16_CR63","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.1109\/LRA.2021.3058072","volume":"6","author":"A Wong","year":"2021","unstructured":"Wong, A., Cicek, S., Soatto, S.: Learning topology from synthetic data for unsupervised depth completion. IEEE Robot. Autom. Lett. 6(2), 1495\u20131502 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"16_CR64","doi-asserted-by":"publisher","first-page":"3120","DOI":"10.1109\/LRA.2021.3062602","volume":"6","author":"A Wong","year":"2021","unstructured":"Wong, A., Fei, X., Hong, B.W., Soatto, S.: An adaptive framework for learning unsupervised depth completion. IEEE Robot. Autom. Lett. 6(2), 3120\u20133127 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"16_CR65","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1109\/LRA.2020.2969938","volume":"5","author":"A Wong","year":"2020","unstructured":"Wong, A., Fei, X., Tsuei, S., Soatto, S.: Unsupervised depth completion from visual inertial odometry. IEEE Robot. Autom. Lett. 5(2), 1899\u20131906 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"16_CR66","doi-asserted-by":"crossref","unstructured":"Wong, A., Soatto, S.: Bilateral cyclic constraint and adaptive regularization for unsupervised monocular depth prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5644\u20135653 (2019)","DOI":"10.1109\/CVPR.2019.00579"},{"key":"16_CR67","doi-asserted-by":"crossref","unstructured":"Wong, A., Soatto, S.: Unsupervised depth completion with calibrated backprojection layers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12747\u201312756 (2021)","DOI":"10.1109\/ICCV48922.2021.01251"},{"key":"16_CR68","doi-asserted-by":"crossref","unstructured":"Xu, D., Ricci, E., Ouyang, W., Wang, X., Sebe, N.: Multi-scale continuous CRFs as sequential deep networks for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5354\u20135362 (2017)","DOI":"10.1109\/CVPR.2017.25"},{"key":"16_CR69","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhu, X., Shi, J., Zhang, G., Bao, H., Li, H.: Depth completion from sparse lidar data with depth-normal constraints. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2811\u20132820 (2019)","DOI":"10.1109\/ICCV.2019.00290"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Yan, Z., Wang, K., Li, X., Zhang, Z., Li, J., Yang, J.: DesNet: decomposed scale-consistent network for unsupervised depth completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3109\u20133117 (2023)","DOI":"10.1609\/aaai.v37i3.25415"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Yang, F., et\u00a0al.: Binding touch to everything: learning unified multimodal tactile representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26340\u201326353 (2024)","DOI":"10.1109\/CVPR52733.2024.02488"},{"key":"16_CR72","doi-asserted-by":"crossref","unstructured":"Yang, N., Stumberg, L.v., Wang, R., Cremers, D.: D3VO: deep depth, deep pose and deep uncertainty for monocular visual odometry. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1281\u20131292 (2020)","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"16_CR73","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wong, A., Soatto, S.: Dense depth posterior (DDP) from single image and sparse range. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3353\u20133362 (2019)","DOI":"10.1109\/CVPR.2019.00347"},{"key":"16_CR74","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1007\/978-3-030-11021-5_43","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"Z Yang","year":"2019","unstructured":"Yang, Z., Wang, P., Wang, Y., Xu, W., Nevatia, R.: Every pixel counts: unsupervised geometry learning with holistic 3D motion understanding. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 691\u2013709. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11021-5_43"},{"key":"16_CR75","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, P., Wang, Y., Xu, W., Nevatia, R.: LEGO: learning edge with geometry all at once by watching videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 225\u2013234 (2018)","DOI":"10.1109\/CVPR.2018.00031"},{"key":"16_CR76","doi-asserted-by":"crossref","unstructured":"Yin, W., Liu, Y., Shen, C., Yan, Y.: Enforcing geometric constraints of virtual normal for depth prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5684\u20135693 (2019)","DOI":"10.1109\/ICCV.2019.00578"},{"key":"16_CR77","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1983\u20131992 (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"16_CR78","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Aggregating feature point cloud for depth completion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8732\u20138743 (2023)","DOI":"10.1109\/ICCV51070.2023.00802"},{"key":"16_CR79","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: WorDepth: variational language prior for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9708\u20139719 (2024)","DOI":"10.1109\/CVPR52733.2024.00927"},{"key":"16_CR80","doi-asserted-by":"crossref","unstructured":"Zhan, H., Garg, R., Weerasekera, C.S., Li, K., Agarwal, H., Reid, I.: Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 340\u2013349 (2018)","DOI":"10.1109\/CVPR.2018.00043"},{"key":"16_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, N., Nex, F., Vosselman, G., Kerle, N.: Lite-mono: a lightweight CNN and transformer architecture for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18537\u201318546 (2023)","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"16_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Funkhouser, T.: Deep depth completion of a single RGB-D image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 175\u2013185 (2018)","DOI":"10.1109\/CVPR.2018.00026"},{"key":"16_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Guo, X., Poggi, M., Zhu, Z., Huang, G., Mattoccia, S.: CompletionFormer: depth completion with convolutions and vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18527\u201318536 (2023)","DOI":"10.1109\/CVPR52729.2023.01777"},{"key":"16_CR84","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: MonoViT: self-supervised monocular depth estimation with a vision transformer. In: 2022 International Conference on 3D Vision (3DV), pp. 668\u2013678. IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"16_CR85","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1851\u20131858 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"16_CR86","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01228-1_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zou","year":"2018","unstructured":"Zou, Y., Luo, Z., Huang, J.-B.: DF-Net: unsupervised joint learning of depth and flow using cross-task consistency. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 38\u201355. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_3"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73039-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:24:54Z","timestamp":1730301894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73039-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730382","9783031730399"],"references-count":86,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73039-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}