{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:51:44Z","timestamp":1744181504298,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729942"},{"type":"electronic","value":"9783031729959"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-72995-9_15","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:18:04Z","timestamp":1732389484000},"page":"253-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-training Room Layout Estimation via\u00a0Geometry-Aware Ray-Casting"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3518-755X","authenticated-orcid":false,"given":"Bolivar","family":"Solarte","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1547-0825","authenticated-orcid":false,"given":"Chin-Hsuan","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9777-4951","authenticated-orcid":false,"given":"Jin-Cheng","family":"Jhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8923-5129","authenticated-orcid":false,"given":"Jonathan","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6191-0134","authenticated-orcid":false,"given":"Yi-Hsuan","family":"Tsai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-8178","authenticated-orcid":false,"given":"Min","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"15_CR1","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: A holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: Learning from RGB-D data in indoor environments. In: International Virtual Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"15_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/978-3-642-41184-7_50","volume-title":"Image Analysis and Processing \u2013 ICIAP 2013","author":"Y-W Chao","year":"2013","unstructured":"Chao, Y.-W., Choi, W., Pantofaru, C., Savarese, S.: Layout estimation of highly cluttered indoor scenes using geometric and semantic cues. In: Petrosino, A. (ed.) ICIAP 2013. LNCS, vol. 8157, pp. 489\u2013499. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-41184-7_50"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Cruz, S., Hutchcroft, W., Li, Y., Khosravan, N., Boyadzhiev, I., Kang, S.B.: Zillow indoor dataset: Annotated floor plans with 360deg panoramas and 3d room layouts. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00217"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Fayyazsanavi, P., et al.: U2rle: Uncertainty-guided 2-stage room layout estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3562\u20133570 (2023)","DOI":"10.1109\/CVPRW59228.2023.00364"},{"issue":"2","key":"15_CR6","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/LRA.2020.2967274","volume":"5","author":"C Fernandez-Labrador","year":"2020","unstructured":"Fernandez-Labrador, C., Facil, J.M., Perez-Yus, A., Demonceaux, C., Civera, J., Guerrero, J.J.: Corners for layout: end-to-end layout recovery from 360 images. IEEE Robot. Autom. Lett. 5(2), 1255\u20131262 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth prediction. In: The International Conference on Computer Vision (ICCV) (October 2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"15_CR8","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/978-3-031-19824-3_36","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXII","author":"W Hutchcroft","year":"2022","unstructured":"Hutchcroft, W., et al.: CoVisPose: co-visibility pose transformer for\u00a0wide-baseline relative pose estimation in\u00a0360$$^\\circ $$ indoor panoramas. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXII, pp. 615\u2013633. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_36"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Xiang, Z., Xu, J., Zhao, M.: Lgt-net: Indoor panoramic room layout estimation with geometry-aware transformer network. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00170"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Badrinarayanan, V., Malisiewicz, T., Rabinovich, A.: Roomnet: End-to-end room layout estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4865\u20134874 (2017)","DOI":"10.1109\/ICCV.2017.521"},{"key":"15_CR11","unstructured":"Lee, D.H., et\u00a0al.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on challenges in representation learning, ICML, p.\u00a0896. Atlanta (2013)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., Dai, H., Han, H., Ding, Y.: Mseg3d: multi-modal 3d semantic segmentation for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21694\u201321704 (June 2023)","DOI":"10.1109\/CVPR52729.2023.02078"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Nejatishahidin, N., et al.: Graph-covis: Gnn-based multi-view panorama global pose estimation. In: CVPR Workshop on Omnidirectional Computer Vision (2023)","DOI":"10.1109\/CVPRW59228.2023.00687"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Doll\u00e1r, P., Girshick, R., Gkioxari, G., He, K.: Data distillation: Towards omni-supervised learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4119\u20134128 (2018)","DOI":"10.1109\/CVPR.2018.00433"},{"key":"15_CR15","unstructured":"Ramakrishnan, S.K., Gokaslan, A., et al.: Habitat-matterport 3d dataset (HM3d): 1000 large-scale 3d environments for embodied AI. In: NeurIPS, Datasets and Benchmarks Track (2021)"},{"key":"15_CR16","first-page":"596","volume":"33","author":"K Sohn","year":"2020","unstructured":"Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv. Neural. Inf. Process. Syst. 33, 596\u2013608 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"3","key":"15_CR17","doi-asserted-by":"publisher","first-page":"6503","DOI":"10.1109\/LRA.2022.3173730","volume":"7","author":"B Solarte","year":"2022","unstructured":"Solarte, B., Liu, Y.C., Wu, C.H., Tsai, Y.H., Sun, M.: 360-dfpe: leveraging monocular 360-layouts for direct floor plan estimation. IEEE Robot. Autom. Lett. 7(3), 6503\u20136510 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"15_CR18","unstructured":"Solarte, B., Wu, C.H., Liu, Y.C., Tsai, Y.H., Sun, M.: 360-mlc: Multi-view layout consistency for self-training and hyper-parameter tuning. In: NeurIPS (2022)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Su, J.W., Peng, C.H., Wonka, P., Chu, H.K.: Gpr-net: Multi-view layout estimation via a geometry-aware panorama registration network. In: CVPR (2023)","DOI":"10.1109\/CVPRW59228.2023.00688"},{"key":"15_CR20","doi-asserted-by":"publisher","unstructured":"Sumikura, S., Shibuya, M., Sakurada, K.: OpenVSLAM: A Versatile Visual SLAM Framework. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2292\u20132295. MM \u201919, ACM, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3343031.3350539","DOI":"10.1145\/3343031.3350539"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Sun, C., Hsiao, C., Sun, M., Chen, H.: Horizonnet: Learning room layout with 1D representation and pano stretch data augmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00114"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.: Hohonet: 360 indoor holistic understanding with latent horizontal features. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00260"},{"key":"15_CR23","unstructured":"Tang, S., Zhang, F., Chen, J., Wang, P., Furukawa, Y.: Mvdiffusion: enabling holistic multi-view image generation with correspondence-aware diffusion. arXiv preprint arXiv:2307.01097 (2023)"},{"key":"15_CR24","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Tran, P.V.: SSLayout360: semi-supervised indoor layout estimation from 360-degree panorama. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01510"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Tsai, G., Xu, C., Liu, J., Kuipers, B.: Real-time indoor scene understanding using bayesian filtering with motion cues. In: 2011 International Conference on Computer Vision, pp. 121\u2013128. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126233"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Wang, F.E., Yeh, Y.H., Sun, M., Chiu, W.C., Tsai, Y.H.: Led2-net: Monocular 360deg layout estimation via differentiable depth rendering. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01276"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Xu, J., Stenger, B., Kerola, T., Tung, T.: Pano2cad: room layout from a single panorama image. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 354\u2013362. IEEE (2017)","DOI":"10.1109\/WACV.2017.46"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Yang, S.T., Wang, F.E., Peng, C.H., Wonka, P., Sun, M., Chu, H.K.: Dula-net: a dual-projection network for estimating room layouts from a single rgb panorama. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3363\u20133372 (2019)","DOI":"10.1109\/CVPR.2019.00348"},{"key":"15_CR30","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1007\/978-3-031-19769-7_37","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part I","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Wen, C., Xue, Z., Gao, Y.: 3D room layout estimation from\u00a0a\u00a0cubemap of\u00a0panorama image via\u00a0deep manhattan hough transform. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part I, pp. 637\u2013654. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_37"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Zou, C., Colburn, A., Shan, Q., Hoiem, D.: Layoutnet: reconstructing the 3d room layout from a single RGB image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2051\u20132059 (2018)","DOI":"10.1109\/CVPR.2018.00219"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Zou, C., et al.: Manhattan room layout reconstruction from a single 360 image: A comparative study of state-of-the-art methods (2020)","DOI":"10.1007\/s11263-020-01426-8"}],"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\/978-3-031-72995-9_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T20:05:26Z","timestamp":1732392326000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72995-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031729942","9783031729959"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72995-9_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 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"}}]}}