{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:19:20Z","timestamp":1742959160942,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031024436"},{"type":"electronic","value":"9783031024443"}],"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\/978-3-031-02444-3_34","type":"book-chapter","created":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T12:02:50Z","timestamp":1652097770000},"page":"447-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Multi-scale Architecture Search for\u00a0Self-supervised Monocular Depth Estimation"],"prefix":"10.1007","author":[{"given":"Jian","family":"Ren","sequence":"first","affiliation":[]},{"given":"Jin","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Zhong","family":"Jin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,10]]},"reference":[{"key":"34_CR1","unstructured":"Brock, A., Lim, T., Ritchie, J.M., Weston, N.: SMASH: one-shot model architecture search through hypernetworks. arXiv preprint arXiv:1708.05344 (2017)"},{"key":"34_CR2","unstructured":"Cai, H., Zhu, L., Han, S.: ProxylessNAS: direct neural architecture search on target task and hardware. In: ICLR (2019)"},{"key":"34_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":"34_CR4","doi-asserted-by":"crossref","unstructured":"Chen, P.Y., Liu, A.H., Liu, Y.C., Wang, Y.C.F.: Towards scene understanding: unsupervised monocular depth estimation with semantic-aware representation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00273"},{"key":"34_CR5","unstructured":"Chen, W., Gong, X., Liu, X., Zhang, Q., Li, Y., Wang, Z.: FasterSeg: searching for faster real-time semantic segmentation. arXiv preprint arXiv:1912.10917 (2019)"},{"key":"34_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: ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"34_CR7","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems (2014)"},{"key":"34_CR8","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S Gao","year":"2019","unstructured":"Gao, S., Cheng, M.M., Zhao, K., Zhang, X.Y., Yang, M.H., Torr, P.H.: Res2Net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43, 652\u2013662 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR9","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., Bg, 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. LNCS, vol. 9912, pp. 740\u2013756. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_45"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"34_CR12","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":"34_CR13","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":"34_CR14","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":"34_CR15","doi-asserted-by":"crossref","unstructured":"Huang, S.Y., Chu, W.T.: Searching by generating: flexible and efficient one-shot NAS with architecture generator. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00104"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Kalia, M., Navab, N., Salcudean, T.: A real-time interactive augmented reality depth estimation technique for surgical robotics. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793610"},{"key":"34_CR17","doi-asserted-by":"publisher","first-page":"2144","DOI":"10.1109\/TPAMI.2014.2316835","volume":"36","author":"K Karsch","year":"2014","unstructured":"Karsch, K., Liu, C., Kang, S.B.: Depth transfer: depth extraction from video using non-parametric sampling. IEEE Trans. Pattern Anal. Mach. Intell. 36, 2144\u20132158 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 3DV (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00017"},{"key":"34_CR22","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: ICLR (2019)"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Liu, M., Salzmann, M., He, X.: Discrete-continuous depth estimation from a single image. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.97"},{"key":"34_CR24","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TPAMI.2019.2930258","volume":"42","author":"C Luo","year":"2019","unstructured":"Luo, C., et al.: Every pixel counts++: joint learning of geometry and motion with 3D holistic understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2624\u20132641 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR25","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":"34_CR26","doi-asserted-by":"crossref","unstructured":"Lyu, X., et al.: HR-depth: high resolution self-supervised monocular depth estimation. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"34_CR27","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tard\u00f3s, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Robot. 31, 1147\u20131163 (2015)","journal-title":"IEEE Trans. Robot."},{"key":"34_CR28","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"34_CR29","unstructured":"Pham, H., Guan, M., Zoph, B., Le, Q., Dean, J.: Efficient neural architecture search via parameters sharing. In: International Conference on Machine Learning (2018)"},{"key":"34_CR30","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.robot.2017.03.019","volume":"93","author":"T Pire","year":"2017","unstructured":"Pire, T., Fischer, T., Castro, G., De Crist\u00f3foris, P., Civera, J., Berlles, J.J.: S-PTAM: stereo parallel tracking and mapping. Robot. Auton. Syst. 93, 27\u201342 (2017)","journal-title":"Robot. Auton. Syst."},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Poggi, M., Tosi, F., Mattoccia, S.: Learning monocular depth estimation with unsupervised trinocular assumptions. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00045"},{"key":"34_CR32","unstructured":"Rashwan, A., Du, X., Yin, X., Li, J.: Dilated SpineNet for semantic segmentation. In: CVPR (2021)"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"34_CR34","unstructured":"Real, E., et al.: Large-scale evolution of image classifiers. In: ICML (2017)"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Sadek, A., Chidlovskii, B.: Self-supervised attention learning for depth and ego-motion estimation. arXiv preprint arXiv:2004.13077 (2020)","DOI":"10.1109\/IROS45743.2020.9340820"},{"key":"34_CR36","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s11263-007-0071-y","volume":"76","author":"A Saxena","year":"2008","unstructured":"Saxena, A., Chung, S.H., Ng, A.Y.: 3-D depth reconstruction from a single still image. Int. J. Comput. Vis. 76, 53\u201369 (2008). https:\/\/doi.org\/10.1007\/s11263-007-0071-y","journal-title":"Int. J. Comput. Vis."},{"key":"34_CR37","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, 824\u2013840 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR38","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"34_CR39","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant CNNs. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00012"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"key":"34_CR42","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"34_CR43","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":"34_CR44","doi-asserted-by":"crossref","unstructured":"Xue, F., Zhuo, G., Huang, Z., Fu, W., Wu, Z., Ang, M.H.: Toward hierarchical self-supervised monocular absolute depth estimation for autonomous driving applications. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9340802"},{"key":"34_CR45","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"34_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"34_CR47","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: ICLR (2017)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-02444-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,4]],"date-time":"2023-02-04T18:34:17Z","timestamp":1675535657000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-02444-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031024436","9783031024443"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-02444-3_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.acpr2021.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","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":"85","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":"55% - 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","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}