{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:21:23Z","timestamp":1742916083757,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031250620"},{"type":"electronic","value":"9783031250637"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25063-7_31","type":"book-chapter","created":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T20:10:15Z","timestamp":1676491815000},"page":"507-523","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LiteDepth: Digging into\u00a0Fast and\u00a0Accurate Depth Estimation on\u00a0Mobile Devices"],"prefix":"10.1007","author":[{"given":"Zhenyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"key":"31_CR1","unstructured":"HUAWEI HiAI engine introduction. https:\/\/developer.huawei.com\/consumer\/en\/doc\/2020315 (2018)"},{"key":"31_CR2","unstructured":"Snapdragon neural processing engine SDK. https:\/\/developer.qualcomm.com\/docs\/snpe\/overview.html (2018)"},{"issue":"1","key":"31_CR3","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1089\/cpb.2007.9935","volume":"11","author":"C Armbr\u00fcster","year":"2008","unstructured":"Armbr\u00fcster, C., Wolter, M., Kuhlen, T., Spijkers, W., Fimm, B.: Depth perception in virtual reality: distance estimations in peri-and extrapersonal space. Cyberpsychol. Behavior 11(1), 9\u201315 (2008)","journal-title":"Cyberpsychol. Behavior"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Barron, J.T.: a general and adaptive robust loss function. In: CVPR, pp. 4331\u20134339 (2019)","DOI":"10.1109\/CVPR.2019.00446"},{"key":"31_CR5","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: CVPR, pp. 4009\u20134018 (2021)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: AutoAlign: pixel-instance feature aggregation for multi-modal 3D object detection. arXiv preprint arXiv:2201.06493 (2022)","DOI":"10.24963\/ijcai.2022\/116"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: AutoAlignv2: deformable feature aggregation for dynamic multi-modal 3D object detection. arXiv preprint arXiv:2207.10316 (2022)","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: Graph-DETR3D: rethinking overlapping regions for multi-view 3D object detection. arXiv preprint arXiv:2204.11582 (2022)","DOI":"10.1145\/3503161.3547859"},{"key":"31_CR9","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NeurIPS (2014)"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: CVPR, pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"issue":"1","key":"31_CR11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0189275","volume":"13","author":"N Gerig","year":"2018","unstructured":"Gerig, N., Mayo, J., Baur, K., Wittmann, F., Riener, R., Wolf, P.: Missing depth cues in virtual reality limit performance and quality of three dimensional reaching movements. PLoS ONE 13(1), e0189275 (2018)","journal-title":"PLoS ONE"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: ICCV, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"31_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-319-54181-5_14","volume-title":"Computer Vision \u2013 ACCV 2016","author":"C Hazirbas","year":"2017","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 213\u2013228. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54181-5_14"},{"key":"31_CR14","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"31_CR15","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: CVPR, pp. 2545\u20132557 (2021)","DOI":"10.1109\/CVPRW53098.2021.00288"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Ignatov, A., et al.: AI benchmark: running deep neural networks on android smartphones. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11021-5_19"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Ignatov, A., et al.: AI benchmark: all about deep learning on smartphones in 2019. In: ICCVW, pp. 3617\u20133635. IEEE (2019)","DOI":"10.1109\/ICCVW.2019.00447"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Ignatov, A., Timofte, R., et al.: Efficient single-image depth estimation on mobile devices, mobile AI & aim 2022 challenge: report. In: ECCV (2022)","DOI":"10.1007\/978-3-031-25066-8_4"},{"key":"31_CR19","unstructured":"Kim, D., Ga, W., Ahn, P., Joo, D., Chun, S., Kim, J.: Global-local path networks for monocular depth estimation with vertical cutDepth. arXiv preprint arXiv:2201.07436 (2022)"},{"key":"31_CR20","unstructured":"Lee, J.H., Han, M.K., Ko, D.W., Suh, I.H.: From big to small: multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)"},{"key":"31_CR21","unstructured":"Li, Z.: Monocular depth estimation toolbox. https:\/\/github.com\/zhyever\/Monocular-Depth-Estimation-Toolbox (2022)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Li, A., Fang, L., Jiang, Q., Liu, X., Jiang, J.: Unsupervised domain adaptation for monocular 3D object detection via self-training. arXiv preprint arXiv:2204.11590 (2022)","DOI":"10.1007\/978-3-031-20077-9_15"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: SimIPU: Simple 2D image and 3D point cloud unsupervised pre-training for spatial-aware visual representations. arXiv preprint arXiv:2112.04680 (2021)","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Liu, X., Jiang, J.: DepthFormer: exploiting long-range correlation and local information for accurate monocular depth estimation. arXiv preprint arXiv:2203.14211 (2022)","DOI":"10.1007\/s11633-023-1458-0"},{"key":"31_CR25","unstructured":"Li, Z., Wang, X., Liu, X., Jiang, J.: BinsFormer: revisiting adaptive bins for monocular depth estimation. arXiv preprint arXiv:2204.00987 (2022)"},{"key":"31_CR26","unstructured":"Lite, T.: Deploy machine learning models on mobile and IoT devices (2019)"},{"key":"31_CR27","unstructured":"Liu, Y., Shu, C., Wang, J., Shen, C.: Structured knowledge distillation for dense prediction. IEEE TPAMI (2020)"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is pseudo-lidar needed for monocular 3d object detection? In: ICCV, pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Patil, V., Sakaridis, C., Liniger, A., Van Gool, L.: P3depth: monocular depth estimation with a piecewise planarity prior. In: CVPR, pp. 1610\u20131621 (2022)","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"31_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Shu, C., Liu, Y., Gao, J., Yan, Z., Shen, C.: Channel-wise knowledge distillation for dense prediction. In: ICCV, pp. 5311\u20135320 (2021)","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"31_CR34","first-page":"7462","volume":"33","author":"V Sitzmann","year":"2020","unstructured":"Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. NeurIPS 33, 7462\u20137473 (2020)","journal-title":"NeurIPS"},{"key":"31_CR35","doi-asserted-by":"crossref","unstructured":"Vu, T.H., Jain, H., Bucher, M., Cord, M., P\u00e9rez, P.: DADA: depth-aware domain adaptation in semantic segmentation. In: ICCV, pp. 7364\u20137373 (2019)","DOI":"10.1109\/ICCV.2019.00746"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Wang, T., Pang, J., Lin, D.: Monocular 3D object detection with depth from motion. arXiv preprint arXiv:2207.12988 (2022)","DOI":"10.1007\/978-3-031-20077-9_23"},{"key":"31_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/978-3-030-01252-6_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W Wang","year":"2018","unstructured":"Wang, W., Neumann, U.: Depth-aware CNN for RGB-D segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 144\u2013161. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_9"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, X., Shi, M., Xian, K., Cao, Z.: Knowledge distillation for fast and accurate monocular depth estimation on mobile devices. In: CVPR, pp. 2457\u20132465 (2021)","DOI":"10.1109\/CVPRW53098.2021.00278"},{"key":"31_CR39","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Weng, X., Kitani, K.: Monocular 3D object detection with pseudo-lidar point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Wofk, D., Ma, F., Yang, T.J., Karaman, S., Sze, V.: FastDepth: fast monocular depth estimation on embedded systems. In: ICRA, pp. 6101\u20136108. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"31_CR42","unstructured":"Yang, G., Tang, H., Ding, M., Sebe, N., Ricci, E.: Transformers solve the limited receptive field for monocular depth prediction. In: ICCV (2021)"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Yin, W., Liu, Y., Shen, C., Yan, Y.: Enforcing geometric constraints of virtual normal for depth prediction. In: ICCV, pp. 5684\u20135693 (2019)","DOI":"10.1109\/ICCV.2019.00578"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"You, Z., Tsai, Y.H., Chiu, W.C., Li, G.: Towards interpretable deep networks for monocular depth estimation. In: ICCV, pp. 12879\u201312888 (2021)","DOI":"10.1109\/ICCV48922.2021.01264"},{"key":"31_CR45","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, pp. 1851\u20131858 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, S., Brazil, G., Liu, X.: The edge of depth: explicit constraints between segmentation and depth. In: CVPR, pp. 13116\u201313125 (2020)","DOI":"10.1109\/CVPR42600.2020.01313"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25063-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T19:08:42Z","timestamp":1710270522000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25063-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250620","9783031250637"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25063-7_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"16 February 2023","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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}