{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:01:41Z","timestamp":1771952501703,"version":"3.50.1"},"publisher-location":"Cham","reference-count":95,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915680","type":"print"},{"value":"9783031915697","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91569-7_16","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:49:55Z","timestamp":1748090995000},"page":"248-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TRICKY 2024 Challenge on\u00a0Monocular Depth from\u00a0Images of\u00a0Specular and\u00a0Transparent Surfaces"],"prefix":"10.1007","author":[{"given":"Pierluigi","family":"Zama Ramirez","sequence":"first","affiliation":[]},{"given":"Alex","family":"Costanzino","sequence":"additional","affiliation":[]},{"given":"Fabio","family":"Tosi","sequence":"additional","affiliation":[]},{"given":"Matteo","family":"Poggi","sequence":"additional","affiliation":[]},{"given":"Luigi","family":"Di Stefano","sequence":"additional","affiliation":[]},{"given":"Jean-Baptiste","family":"Weibel","sequence":"additional","affiliation":[]},{"given":"Dominik","family":"Bauer","sequence":"additional","affiliation":[]},{"given":"Doris","family":"Antensteiner","sequence":"additional","affiliation":[]},{"given":"Markus","family":"Vincze","sequence":"additional","affiliation":[]},{"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yachuan","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Junrui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yiran","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jinghong","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Liao","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Ziyang","family":"Song","sequence":"additional","affiliation":[]},{"given":"Zerong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ruijie","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jiang","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jinqiu","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Pihai","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yuanqi","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Wenbo","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Kui","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Mykola","family":"Lavreniuk","sequence":"additional","affiliation":[]},{"given":"Pengzhi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jui-Lin","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Aleotti, F., Tosi, F., Poggi, M., Mattoccia, S.: Generative adversarial networks for unsupervised monocular depth prediction. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11009-3_20"},{"issue":"1","key":"16_CR2","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3390\/s21010015","volume":"21","author":"F Aleotti","year":"2020","unstructured":"Aleotti, F., Zaccaroni, G., Bartolomei, L., Poggi, M., Tosi, F., Mattoccia, S.: Real-time single image depth perception in the wild with handheld devices. Sensors 21(1), 15 (2020)","journal-title":"Sensors"},{"key":"16_CR3","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: Zoedepth: Zero-shot transfer by combining relative and metric depth (2023)"},{"key":"16_CR4","unstructured":"Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. In: Proceedings of the NeurIPS (2016)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Qian, S., Fan, D., Kojima, N., Hamilton, M., Deng, J.: OASIS: a large-scale dataset for single image 3D in the wild. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00076"},{"key":"16_CR6","unstructured":"Cho, J., Min, D., Kim, Y., Sohn, K.: DIML\/CVL RGB-D dataset: 2M RGB-d images of natural indoor and outdoor scenes. arXiv preprint arXiv:2110.11590 (2021)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Choi, J., Jung, D., Lee, Y., Kim, D., Manocha, D., Lee, D.: SelfDeco: self-supervised monocular depth completion in challenging indoor environments. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 467\u2013474. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9560831"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Costanzino, A., Zama\u00a0Ramirez, P., Poggi, M., Tosi, F., Mattoccia, S., Di\u00a0Stefano, L.: Learning depth estimation for transparent and mirror surfaces. In: The IEEE International Conference on Computer Vision (2023), iCCV","DOI":"10.1109\/ICCV51070.2023.00848"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Duan, Y., Guo, X., Zhu, Z.: DiffusionDepth: Diffusion denoising approach for monocular depth estimation. arXiv preprint arXiv:2303.05021 (2023)","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Eftekhar, A., Sax, A., Malik, J., Zamir, A.: OmniData: a scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In: ICCV, pp. 10786\u201310796 (2021)","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"16_CR11","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Proceedings of the NeurIPS (2014)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: GeoWizard: unleashing the diffusion priors for 3D geometry estimation from a single image. arXiv preprint arXiv:2403.12013 (2024)","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"16_CR13","unstructured":"Gaidon, A., et al.: Dense depth for autonomous driving (DDAD) challenge (2021). (https:\/\/sites.google.com\/view\/mono3d-workshop)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Gasperini, S., Morbitzer, N., Jung, H., Navab, N., Tombari, F.: Robust monocular depth estimation under challenging conditions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00751"},{"issue":"11","key":"16_CR15","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013). https:\/\/doi.org\/10.1177\/0278364913491297","journal-title":"Int. J. Robot. Res."},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"16_CR17","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 CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"16_CR18","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 ICCV (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"16_CR19","unstructured":"GonzalezBello, J.L., Kim, M.: Forget about the lidar: Self-supervised depth estimators with med probability volumes. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 12626\u201312637. Curran Associates, Inc. (2020), https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/951124d4a093eeae83d9726a20295498-Paper.pdf"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. arXiv preprint arXiv:2002.12319 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Vasiljevic, I., Chen, D., Ambru\u015f, R., Gaidon, A.: Towards zero-shot scale-aware monocular depth estimation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Guo, X., Li, H., Yi, S., Ren, J., Wang, X.: Learning monocular depth by distilling cross-domain stereo networks. In: Proceedings of the ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"16_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"16_CR24","doi-asserted-by":"publisher","unstructured":"Hornauer, J., Belagiannis, V.: Gradient-based uncertainty for monocular depth estimation. In: European Conference on Computer Vision, pp. 613\u2013630. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_35","DOI":"10.1007\/978-3-031-20044-1_35"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Hu, M., et al.: Metric3d V2: a versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. arXiv preprint arXiv:2404.15506 (2024)","DOI":"10.1109\/TPAMI.2024.3444912"},{"issue":"10","key":"16_CR26","doi-asserted-by":"publisher","first-page":"2702","DOI":"10.1109\/TPAMI.2019.2926463","volume":"42","author":"X Huang","year":"2019","unstructured":"Huang, X., Wang, P., Cheng, X., Zhou, D., Geng, Q., Yang, R.: The apolloscape open dataset for autonomous driving and its application. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2702\u20132719 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Ignatov, A., Malivenko, G., Plowman, D., Shukla, S., Timofte, R.: Fast and accurate single-image depth estimation on mobile devices, mobile AI 2021 challenge: report. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2545\u20132557 (2021)","DOI":"10.1109\/CVPRW53098.2021.00288"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: DDP: diffusion model for dense visual prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Jiang, H., Larsson, G., Maire Greg\u00a0Shakhnarovich, M., Learned-Miller, E.: Self-supervised relative depth learning for urban scene understanding. In: Proceedings of the ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_2"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Johnston, A., Carneiro, G.: Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. In: Proceedings of the CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"16_CR33","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. LNCS, vol. 12365, pp. 582\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_35"},{"key":"16_CR34","unstructured":"Kretzschmar, H., et al.: Argoverse stereo competition (2021, 2022). (https:\/\/cvpr2022.wad.vision\/)"},{"key":"16_CR35","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_CR36","unstructured":"Lavreniuk, M., Bhat, S.F., M\u00fcller, M., Wonka, P.: EVP: enhanced visual perception using inverse multi-attentive feature refinement and regularized image-text alignment (2023). https:\/\/arxiv.org\/abs\/2312.08548"},{"key":"16_CR37","unstructured":"Li, H., Gordon, A., Zhao, H., Casser, V., Angelova, A.: Unsupervised monocular depth learning in dynamic scenes. In: Kober, J., Ramos, F., Tomlin, C. (eds.) Proceedings of the 2020 Conference on Robot Learning. Proceedings of Machine Learning Research, vol.\u00a0155, pp. 1908\u20131917. PMLR (2021). https:\/\/proceedings.mlr.press\/v155\/li21a.html"},{"key":"16_CR38","unstructured":"Li, H., Poggi, M., Tosi, F., Mattoccia, S., et\u00a0al.: On-site adaptation for monocular depth estimation with a static camera. In: BMVC, pp. 901\u2013907 (2023)"},{"key":"16_CR39","unstructured":"Li, P., Ding, Y., Wang, H., Tang, C., Li, Z.: The devil is in the edges: monocular depth estimation with edge-aware consistency fusion. arXiv preprint arXiv:2404.00373 (2024)"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2041\u20132050 (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Li, Z., Bhat, S.F., Wonka, P.: PatchFusion: an end-to-end tile-based framework for high-resolution monocular metric depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00955"},{"key":"16_CR42","doi-asserted-by":"publisher","unstructured":"Liang, Y., Zhang, Z., Xian, C., He, S.: Delving into multi-illumination monocular depth estimation: a new dataset and method. IEEE Trans. Multimedia, 1\u201315 (2024). https:\/\/doi.org\/10.1109\/TMM.2024.3353544","DOI":"10.1109\/TMM.2024.3353544"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Lin, J., Wang, G., Lau, R.W.: Progressive mirror detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3697\u20133705 (2020)","DOI":"10.1109\/CVPR42600.2020.00375"},{"key":"16_CR44","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_CR45","doi-asserted-by":"crossref","unstructured":"Mei, H., et al.: Don\u2019t hit me! glass detection in real-world scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3687\u20133696 (2020)","DOI":"10.1109\/CVPR42600.2020.00374"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Miangoleh, S.M.H., Dille, S., Mai, L., Paris, S., Aksoy, Y.: Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9685\u20139694 (2021)","DOI":"10.1109\/CVPR46437.2021.00956"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Moon, J., Bello, J.L.G., Kwon, B., Kim, M.: From-ground-to-objects: Coarse-to-fine self-supervised monocular depth estimation of dynamic objects with ground contact prior. arXiv preprint arXiv:2312.10118 (2023)","DOI":"10.1109\/CVPR52733.2024.01001"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Nathan\u00a0Silberman, Derek\u00a0Hoiem, P.K., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: Towards real-time unsupervised monocular depth estimation on CPU. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5848\u20135854. IEEE (2018)","DOI":"10.1109\/IROS.2018.8593814"},{"key":"16_CR50","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 CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"16_CR51","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_CR52","doi-asserted-by":"crossref","unstructured":"Ramamonjisoa, M., Du, Y., Lepetit, V.: Predicting sharp and accurate occlusion boundaries in monocular depth estimation using displacement fields. In: Proceedings of the CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01466"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Ramirez, P.Z., et\u00a0al.: NTIRE 2023 challenge on HR depth from images of specular and transparent surfaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1384\u20131395 (2023)","DOI":"10.1109\/CVPRW59228.2023.00143"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"16_CR55","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. (2020)"},{"key":"16_CR56","doi-asserted-by":"crossref","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) (2022)","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Jampani, V., Balles, L., Kim, K., Sun, D., Wulff, J., Black, M.J.: 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"},{"key":"16_CR58","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":"16_CR59","doi-asserted-by":"crossref","unstructured":"Sajjan, S., Moore, M., Pan, M., Nagaraja, G., Lee, J., Zeng, A., Song, S.: Clear grasp: 3D shape estimation of transparent objects for manipulation. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 3634\u20133642. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197518"},{"key":"16_CR60","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: depth perception from a single still image. In: Proceedings of the AAAI (2008)"},{"key":"16_CR61","unstructured":"Saxena, S., et al.: The surprising effectiveness of diffusion models for optical flow and monocular depth estimation. arXiv preprint arXiv:2306.01923 (2023)"},{"key":"16_CR62","unstructured":"Saxena, S., Kar, A., Norouzi, M., Fleet, D.J.: Monocular depth estimation using diffusion models. arXiv preprint arXiv:2302.14816 (2023)"},{"key":"16_CR63","unstructured":"Shao, J., Yang, Y., Zhou, H., Zhang, Y., Shen, Y., Poggi, M., Liao, Y.: Learning temporally consistent video depth from video diffusion priors. arXiv preprint arXiv:2406.01493 (2024)"},{"key":"16_CR64","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"Spencer, J., et al.: The monocular depth estimation challenge. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, pp. 623\u2013632 (2023)","DOI":"10.1109\/WACVW58289.2023.00069"},{"key":"16_CR66","unstructured":"Spencer, J., et al.: The second monocular depth estimation challenge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2023)"},{"key":"16_CR67","unstructured":"Spencer, J., Russell, C., Hadfield, S., Bowden, R.: Kick back & relax: learning to reconstruct the world by watching SlowTV. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15768\u201315779 (23)"},{"key":"16_CR68","unstructured":"Spencer, J., Russell, C., Hadfield, S., Bowden, R.: Kick back & relax++: scaling beyond ground-truth depth with SlowTV & CribsTV. arXiv preprint arXiv:2403.01569 (2024)"},{"key":"16_CR69","unstructured":"Spencer, J., et al.: The third monocular depth estimation challenge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2024)"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D slam systems. In: Proceedings of the International Conference on Intelligent Robot Systems (IROS) (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"16_CR71","unstructured":"Sun, Y., Hariharan, B.: Dynamo-depth: Fixing unsupervised depth estimation for dynamical scenes. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"16_CR72","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with fourier convolutions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2149\u20132159 (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"16_CR73","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 (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01003"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Tosi, F., Aleotti, F., Ramirez, P.Z., Poggi, M., Salti, S., Stefano, L.D., Mattoccia, S.: Distilled semantics for comprehensive scene understanding from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00471"},{"key":"16_CR75","doi-asserted-by":"crossref","unstructured":"Tosi, F., Zama Ramirez, P., Poggi, M.: Diffusion models for monocular depth estimation: overcoming challenging conditions. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73337-6_14"},{"key":"16_CR76","doi-asserted-by":"crossref","unstructured":"Wang, L., Zhang, J., Wang, Y., Lu, H., Ruan, X.: CLIFFNet for monocular depth estimation with hierarchical embedding loss. In: Proceedings of the ECCV (2020)","DOI":"10.1007\/978-3-030-58558-7_19"},{"key":"16_CR77","doi-asserted-by":"crossref","unstructured":"Watson, J., Firman, M., Brostow, G.J., Turmukhambetov, D.: Self-supervised monocular depth hints. In: Proceedings of the ICCV (2019)","DOI":"10.1109\/ICCV.2019.00225"},{"key":"16_CR78","doi-asserted-by":"publisher","unstructured":"Xie, E., Wang, W., Wang, W., Ding, M., Shen, C., Luo, P.: Segmenting transparent objects in the wild. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XIII 16, pp. 696\u2013711. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_41","DOI":"10.1007\/978-3-030-58601-0_41"},{"key":"16_CR79","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"16_CR80","unstructured":"Yang, L., et al.: Depth anything V2. arXiv:2406.09414 (2024)"},{"key":"16_CR81","unstructured":"Yin, W., et al.: DiversedDepth: affine-invariant depth prediction using diverse data. arXiv preprint arXiv:2002.00569 (2020)"},{"key":"16_CR82","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Metric3D: towards zero-shot metric 3D prediction from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9043\u20139053 (2023)","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"16_CR83","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Metric3D: towards zero-shot metric 3D prediction from a single image. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"16_CR84","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Learning to recover 3D scene shape from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 204\u2013213 (2021)","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"16_CR85","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_CR86","unstructured":"Zama\u00a0Ramirez, P., et al.: Booster: a benchmark for depth from images of specular and transparent surfaces. arXiv preprint arXiv:2301.08245 (2023)"},{"key":"16_CR87","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/978-3-030-20893-6_19","volume-title":"Computer Vision \u2013 ACCV 2018","author":"P Zama Ramirez","year":"2019","unstructured":"Zama Ramirez, P., Poggi, M., Tosi, F., Mattoccia, S., Di Stefano, L.: Geometry meets semantics for semi-supervised monocular depth estimation. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 298\u2013313. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_19"},{"key":"16_CR88","unstructured":"Zama\u00a0Ramirez, P., et al.: NTIRE 2024 challenge on HR depth from images of specular and transparent surfaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2024)"},{"key":"16_CR89","doi-asserted-by":"crossref","unstructured":"Zama\u00a0Ramirez, P., Tosi, F., Poggi, M., Salti, S., Mattoccia, S., Di\u00a0Stefano, L.: Open challenges in deep stereo: The booster dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21168\u201321178 (2022)","DOI":"10.1109\/CVPR52688.2022.02049"},{"key":"16_CR90","unstructured":"Zendel, O., et al.: The robust vision challenge (2018, 2020, 2022). (http:\/\/www.robustvision.net\/)"},{"key":"16_CR91","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: GasMono: geometry-aided self-supervised monocular depth estimation for indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16209\u201316220 (2023)","DOI":"10.1109\/ICCV51070.2023.01485"},{"key":"16_CR92","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_CR93","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, H., Shen, X., Jia, J.: Unsupervised learning of stereo matching. In: The IEEE International Conference on Computer Vision (ICCV). IEEE (2017)","DOI":"10.1109\/ICCV.2017.174"},{"key":"16_CR94","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_CR95","doi-asserted-by":"crossref","unstructured":"Zou, Y., Luo, Z., Huang, J.B.: DF-Net: unsupervised joint learning of depth and flow using cross-task consistency. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 36\u201353 (2018)","DOI":"10.1007\/978-3-030-01228-1_3"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91569-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:50:24Z","timestamp":1748091024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91569-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915680","9783031915697"],"references-count":95,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91569-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}