{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T05:24:44Z","timestamp":1749792284784,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031208676"},{"type":"electronic","value":"9783031208683"}],"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\/978-3-031-20868-3_32","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:29:12Z","timestamp":1667518152000},"page":"438-451","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Self-supervised Indoor 360-Degree Depth Estimation via\u00a0Structural Regularization"],"prefix":"10.1007","author":[{"given":"Weifeng","family":"Kong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiudan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiesong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"32_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1007\/978-3-030-01231-1_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Zioulis","year":"2018","unstructured":"Zioulis, N., Karakottas, A., Zarpalas, D., Daras, P.: OmniDepth: dense depth estimation for\u00a0indoors spherical panoramas. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 453\u2013471. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_28"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Wang, F.-E., Yeh, Y.-H., Sun, M., Chiu, W.-C., Tsai, Y.-H.: Bifuse: monocular 360 depth estimation via bi-projection fusion. In: Proceedings CVPR, pp. 462\u2013471 (2020)","DOI":"10.1109\/CVPR42600.2020.00054"},{"key":"32_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-030-20873-8_4","volume-title":"Computer Vision \u2013 ACCV 2018","author":"F-E Wang","year":"2019","unstructured":"Wang, F.-E., et al.: Self-supervised learning of depth and camera motion from 360$$^\\circ $$ videos. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11365, pp. 53\u201368. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20873-8_4"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Zioulis, N., Karakottas, A., Zarpalas, D., Alvarez, F., Daras, P.: Spherical view synthesis for self-supervised 360 depth estimation. In: Proceedings 3DV, pp. 690\u2013699. IEEE (2019)","DOI":"10.1109\/3DV.2019.00081"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Lai, Z., Chen, D., Su, K.: Olanet: self-supervised $$360^{\\circ }$$ depth estimation with effective distortion-aware view synthesis and l1 smooth regularization. In: Proceedings ICME, pp. 1\u20136. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428439"},{"key":"32_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1007\/978-3-319-10599-4_43","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Zhang","year":"2014","unstructured":"Zhang, Y., Song, S., Tan, P., Xiao, J.: PanoContext: a whole-room 3D context model for panoramic scene understanding. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 668\u2013686. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_43"},{"issue":"4","key":"32_CR7","doi-asserted-by":"publisher","first-page":"3153","DOI":"10.1109\/LRA.2018.2850532","volume":"3","author":"C Fernandez-Labrador","year":"2018","unstructured":"Fernandez-Labrador, C., Perez-Yus, A., Lopez-Nicolas, G., Guerrero, J.J.: Layouts from panoramic images with geometry and deep learning. IEEE Robot. Autom. Lett. 3(4), 3153\u20133160 (2018)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"32_CR8","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 CVPR, pp. 225\u2013234 (2018)","DOI":"10.1109\/CVPR.2018.00031"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Li, B., Huang, Y., Liu, Z., Zou, D., Yu, W.: StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation. In: Proceedings CVPR, pp. 663\u2013673 (2021)","DOI":"10.1109\/ICCV48922.2021.01243"},{"issue":"2","key":"32_CR10","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167\u2013181 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"32_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-030-58586-0_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Yu","year":"2020","unstructured":"Yu, Z., Jin, L., Gao, S.: P$$^{2}$$Net: patch-match and plane-regularization for unsupervised indoor depth estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 206\u2013222. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_13"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency, In: Proceedings CVPR, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"32_CR13","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"key":"32_CR14","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings AISTATS, pp. 249\u2013256. JMLR (2010)"},{"key":"32_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1007\/978-3-030-01237-3_48","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., et al.: ActiveStereoNet: end-to-end self-supervised learning for active stereo systems. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 802\u2013819. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_48"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: Proceedings CVPR, pp. 1746\u20131754 (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: Learning from RGB-D data in indoor environments. In: Proceedings 3DV (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"32_CR18","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D\u20133D-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)"},{"issue":"2","key":"32_CR19","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1109\/LRA.2021.3058957","volume":"6","author":"H Jiang","year":"2021","unstructured":"Jiang, H., Sheng, Z., Zhu, S., Dong, Z., Huang, R.: Unifuse: Unidirectional fusion for 360 panorama depth estimation. IEEE Robot. Autom. Lett. 6(2), 1519\u20131526 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Cheng, H.-T., Chao, C.-H., Dong, J.-D., Wen, H.-K., Liu, T.-L., Sun, M.: Cube padding for weakly-supervised saliency prediction in 360 videos. In: Proceedings CVPR, pp. 1420\u20131429 (2018)","DOI":"10.1109\/CVPR.2018.00154"},{"key":"32_CR21","first-page":"529","volume":"30","author":"Y-C Su","year":"2017","unstructured":"Su, Y.-C., Grauman, K.: Learning spherical convolution for fast features from 360 imagery. Adv. NIPS 30, 529\u2013539 (2017)","journal-title":"Adv. NIPS"},{"key":"32_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-030-01270-0_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Tateno","year":"2018","unstructured":"Tateno, K., Navab, N., Tombari, F.: Distortion-aware convolutional filters for dense prediction in panoramic images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 732\u2013750. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_43"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Yang, S., Song, Y., Kaess, M., Scherer, S.: Pop-up slam: Semantic monocular plane slam for low-texture environments. In: Proceedings IROS, pp. 1222\u20131229. IEEE (2016)","DOI":"10.1109\/IROS.2016.7759204"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Wang, R., Geraghty, D., Matzen, K., Szeliski, R., Frahm, J.-M.: VPLNet: deep single view normal estimation with vanishing points and lines. In: Proceedings CVPR, pp. 689\u2013698 (2020)","DOI":"10.1109\/CVPR42600.2020.00077"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Lu, X., Yaoy, J., Li, H., Liu, Y., Zhang, X.: 2-line exhaustive searching for real-time vanishing point estimation in manhattan world. In: Proceedings WACV, pp. 345\u2013353. IEEE (2017)","DOI":"10.1109\/WACV.2017.45"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Yu, Z., Zheng, J., Lian, D., Zhou, Z., Gao, S.: Single-image piece-wise planar 3D reconstruction via associative embedding. In: Proceedings CVPR, pp. 1029\u20131037 (2019)","DOI":"10.1109\/CVPR.2019.00112"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Shah, A., Kadam, E., Shah, H., Shinde, S., Shingade, S.: Deep residual networks with exponential linear unit. In: Proceedings of the Third International Symposium on Computer Vision and the Internet, pp. 59\u201365 (2016)","DOI":"10.1145\/2983402.2983406"},{"key":"32_CR28","unstructured":"Liu, R., et al.: An intriguing failing of convolutional neural networks and the coordconv solution. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"32_CR29","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.image.2018.05.005","volume":"69","author":"R Monroy","year":"2018","unstructured":"Monroy, R., Lutz, S., Chalasani, T., Smolic, A.: Salnet360: saliency maps for omni-directional images with CNN. Sig. Process. Image Commun. 69, 26\u201334 (2018)","journal-title":"Sig. Process. Image Commun."},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Khasanova, R., Frossard, P.: Graph-based classification of omnidirectional images. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 869\u2013878 (2017)","DOI":"10.1109\/ICCVW.2017.106"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.-T.: HoHoNet: 360 indoor holistic understanding with latent horizontal features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2573\u20132582 (2021)","DOI":"10.1109\/CVPR46437.2021.00260"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Coughlan, J.M., Yuille, A.L.: Manhattan world: compass direction from a single image by bayesian inference. In: Proceedings of the seventh IEEE international conference on computer vision, vol. 2, pp. 941\u2013947. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790349"},{"issue":"4","key":"32_CR33","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1109\/TRO.2019.2915140","volume":"35","author":"D Zou","year":"2019","unstructured":"Zou, D., Wu, Y., Pei, L., Ling, H., Yu, W.: Structvio: visual-inertial odometry with structural regularity of man-made environments. IEEE Trans. Rob. 35(4), 999\u20131013 (2019)","journal-title":"IEEE Trans. Rob."},{"key":"32_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-01234-2_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Tulsiani","year":"2018","unstructured":"Tulsiani, S., Tucker, R., Snavely, N.: Layer-structured 3D scene inference via view synthesis. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 311\u2013327. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_19"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Guo, Y., Yan, Z., Huang, X., Duan, Y., Ren, L.: Omnifusion: 360 monocular depth estimation via geometry-aware fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2801\u20132810 (2022)","DOI":"10.1109\/CVPR52688.2022.00282"},{"key":"32_CR36","unstructured":"Bai, J., Lai, S., Qin, H., Guo, J., Guo, Y.: GlpanoDepth: global-to-local panoramic depth estimation. arXiv preprint arXiv:2202.02796 (2022)"},{"key":"32_CR37","unstructured":"Area, M.R., Yuan, M., Richardt, C.: 360monodepth: high-resolution $$360^{\\circ }$$ monocular depth estimation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2022: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20868-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:43:57Z","timestamp":1667519037000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20868-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031208676","9783031208683"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20868-3_32","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":"4 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shangai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"10 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pricai.org\/2022\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"432","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":"91","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":"39","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":"21% - 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":"7-8","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":"n\/a","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)"}}]}}