{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T19:23:25Z","timestamp":1771961005464,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T00:00:00Z","timestamp":1612828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T00:00:00Z","timestamp":1612828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100007297","name":"Office of Naval Research Global","doi-asserted-by":"publisher","award":["N00014-16-1-2007"],"award-info":[{"award-number":["N00014-16-1-2007"]}],"id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"crossref","award":["107-2221-E-007-088-MY3"],"award-info":[{"award-number":["107-2221-E-007-088-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"crossref"}]},{"name":"iStaging Corp. fund"},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"crossref","award":["108-2218-E-007-050-MY3"],"award-info":[{"award-number":["108-2218-E-007-050-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11263-020-01426-8","type":"journal-article","created":{"date-parts":[[2021,2,10]],"date-time":"2021-02-10T02:17:08Z","timestamp":1612923428000},"page":"1410-1431","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Manhattan Room Layout Reconstruction from a Single $$360^{\\circ }$$ Image: A Comparative Study of State-of-the-Art Methods"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2537-284X","authenticated-orcid":false,"given":"Chuhang","family":"Zou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jheng-Wei","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Han","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Colburn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Wonka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Kuo","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derek","family":"Hoiem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,9]]},"reference":[{"key":"1426_CR1","unstructured":"Armeni, I., Sax, A., Zamir, A. R., & Savarese, S. (2017). Joint 2D\u20133D-semantic data for indoor scene understanding. arXiv:1702.01105."},{"key":"1426_CR2","doi-asserted-by":"crossref","unstructured":"Cabral, R., & Furukawa, Y. (2014). Piecewise planar and compact floorplan reconstruction from images. In CVPR (pp. 628\u2013635).","DOI":"10.1109\/CVPR.2014.546"},{"key":"1426_CR3","doi-asserted-by":"crossref","unstructured":"Chang, A., Dai, A., Funkhouser, T., Halber, M., Niessner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2017). Matterport3d: Learning from rgb-d data in indoor environments. arXiv:1709.06158.","DOI":"10.1109\/3DV.2017.00081"},{"key":"1426_CR4","doi-asserted-by":"crossref","unstructured":"Coughlan, J. M., & Yuille, A. L. (1999). Manhattan world: Compass direction from a single image by Bayesian inference. In ICCV, IEEE (vol. 2, pp. 941\u2013947).","DOI":"10.1109\/ICCV.1999.790349"},{"key":"1426_CR5","doi-asserted-by":"crossref","unstructured":"Dasgupta, S., Fang, K., Chen, K., & Savarese, S. (2016). Delay: Robust spatial layout estimation for cluttered indoor scenes. In CVPR (pp. 616\u2013624).","DOI":"10.1109\/CVPR.2016.73"},{"key":"1426_CR6","doi-asserted-by":"crossref","unstructured":"Del\u00a0Pero, L., Bowdish, J., Fried, D., Kermgard, B., Hartley, E., & Barnard, K. (2012). Bayesian geometric modeling of indoor scenes. In CVPR (pp. 2719\u20132726).","DOI":"10.1109\/CVPR.2012.6247994"},{"key":"1426_CR7","doi-asserted-by":"crossref","unstructured":"Del\u00a0Pero, L., Bowdish, J., Kermgard, B., Hartley, E., & Barnard, K. (2013). Understanding Bayesian rooms using composite 3d object models. In CVPR (pp. 153\u2013160).","DOI":"10.1109\/CVPR.2013.27"},{"key":"1426_CR8","doi-asserted-by":"crossref","unstructured":"Delage, E., Lee, H., & Ng, A. Y. (2006). A dynamic Bayesian network model for autonomous 3d reconstruction from a single indoor image. In CVPR, IEEE (vol. 2, pp. 2418\u20132428).","DOI":"10.1109\/CVPR.2006.23"},{"key":"1426_CR9","doi-asserted-by":"crossref","unstructured":"Flint, A., Mei, C., Murray, D., & Reid, I. (2010). A dynamic programming approach to reconstructing building interiors. In European conference on computer vision (pp. 394\u2013407). Springer.","DOI":"10.1007\/978-3-642-15555-0_29"},{"key":"1426_CR10","doi-asserted-by":"crossref","unstructured":"Fukano, K., Mochizuki, Y., Iizuka, S., Simo-Serra, E., Sugimoto, A., & Ishikawa, H. (2016). Room reconstruction from a single spherical image by higher-order energy minimization. In 2016 23rd international conference on pattern recognition (ICPR) (pp. 1768\u20131773).","DOI":"10.1109\/ICPR.2016.7899892"},{"key":"1426_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1426_CR12","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., & Forsyth, D. (2009). Recovering the spatial layout of cluttered rooms. In ICCV.","DOI":"10.1109\/ICCV.2009.5459411"},{"key":"1426_CR13","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., & Forsyth, D. (2010). Thinking inside the box: Using appearance models and context based on room geometry. In ECCV (pp. 224\u2013237).","DOI":"10.1007\/978-3-642-15567-3_17"},{"key":"1426_CR14","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A. A., & Hebert, M. (2005). Geometric context from a single image. In ICCV, IEEE (vol. 1, pp. 654\u2013661).","DOI":"10.1109\/ICCV.2005.107"},{"issue":"1","key":"1426_CR15","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s11263-006-0031-y","volume":"75","author":"D Hoiem","year":"2007","unstructured":"Hoiem, D., Efros, A. A., & Hebert, M. (2007). Recovering surface layout from an image. International Journal of Computer Vision, 75(1), 151\u2013172.","journal-title":"International Journal of Computer Vision"},{"key":"1426_CR16","doi-asserted-by":"crossref","unstructured":"Izadinia, H., Shan, Q., & Seitz, S. M. (2017). Im2cad. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5134\u20135143).","DOI":"10.1109\/CVPR.2017.260"},{"key":"1426_CR17","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980."},{"key":"1426_CR18","doi-asserted-by":"crossref","unstructured":"Lee, C. Y., Badrinarayanan, V., Malisiewicz, T., & Rabinovich, A. (2017). Roomnet: End-to-end room layout estimation. In Proceedings of the IEEE international conference on computer vision (pp. 4865\u20134874).","DOI":"10.1109\/ICCV.2017.521"},{"key":"1426_CR19","unstructured":"Lee, D., Gupta, A., Hebert, M., & Kanade, T. (2010). Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In NIPS (pp. 1288\u20131296)."},{"key":"1426_CR20","doi-asserted-by":"crossref","unstructured":"Lee, D. C., Hebert, M., & Kanade, T. (2009). Geometric reasoning for single image structure recovery. In CVPR (pp. 2136\u20132143). IEEE.","DOI":"10.1109\/CVPR.2009.5206872"},{"key":"1426_CR21","doi-asserted-by":"crossref","unstructured":"Liu, C., Kohli, P., & Furukawa, Y. (2016). Layered scene decomposition via the occlusion-crf. In CVPR (pp. 165\u2013173).","DOI":"10.1109\/CVPR.2016.25"},{"key":"1426_CR22","unstructured":"Liu, C., Schwing, A. G., Kundu, K., Urtasun, R., & Fidler, S. (2015). Rent3d: Floor-plan priors for monocular layout estimation. In CVPR (pp. 3413\u20133421)."},{"key":"1426_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., Wu, J., & Furukawa, Y. (2018). Floornet: A unified framework for floorplan reconstruction from 3d scans. In Proceedings of the European conference on computer vision (ECCV) (pp. 201\u2013217).","DOI":"10.1007\/978-3-030-01231-1_13"},{"key":"1426_CR24","doi-asserted-by":"crossref","unstructured":"Mallya, A., & Lazebnik, S. (2015). Learning informative edge maps for indoor scene layout prediction. In ICCV (pp. 936\u2013944).","DOI":"10.1109\/ICCV.2015.113"},{"issue":"4","key":"1426_CR25","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/2766995","volume":"34","author":"A Monszpart","year":"2015","unstructured":"Monszpart, A., Mellado, N., Brostow, G. J., & Mitra, N. J. (2015). Rapter: Rebuilding man-made scenes with regular arrangements of planes. ACM Transactions on Graphics, 34(4), 103.","journal-title":"ACM Transactions on Graphics"},{"key":"1426_CR26","first-page":"127","volume":"11","author":"RA Newcombe","year":"2011","unstructured":"Newcombe, R. A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., et al. (2011). Kinectfusion: Real-time dense surface mapping and tracking. ISMAR, 11, 127\u2013136.","journal-title":"ISMAR"},{"key":"1426_CR27","doi-asserted-by":"crossref","unstructured":"Pintore, G., Garro, V., Ganovelli, F., Gobbetti, E., & Agus, M. (2016). Omnidirectional image capture on mobile devices for fast automatic generation of 2.5 d indoor maps. In 2016 IEEE winter conference on applications of computer vision (WACV) (pp. 1\u20139). IEEE.","DOI":"10.1109\/WACV.2016.7477631"},{"key":"1426_CR28","doi-asserted-by":"crossref","unstructured":"Ramalingam, S., & Brand, M. (2013). Lifting 3d manhattan lines from a single image. In Proceedings of the IEEE international conference on computer vision (pp. 497\u2013504).","DOI":"10.1109\/ICCV.2013.67"},{"key":"1426_CR29","doi-asserted-by":"crossref","unstructured":"Ramalingam, S., Pillai, J. K., Jain, A., & Taguchi, Y. (2013). Manhattan junction catalogue for spatial reasoning of indoor scenes. In CVPR (pp. 3065\u20133072).","DOI":"10.1109\/CVPR.2013.394"},{"key":"1426_CR30","doi-asserted-by":"crossref","unstructured":"Ren, Y., Li, S., Chen, C., & Kuo, C. C. J. (2016). A coarse-to-fine indoor layout estimation (cfile) method. In Asian conference on computer vision (pp. 36\u201351). Springer.","DOI":"10.1007\/978-3-319-54193-8_3"},{"key":"1426_CR31","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., & Monro, S. (1951). A stochastic approximation method. The Annals of Mathematical Statistics, 22, 400\u2013407.","journal-title":"The Annals of Mathematical Statistics"},{"key":"1426_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International conference on medical image computing and computer-assisted intervention (pp. 234\u2013241). Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1426_CR33","doi-asserted-by":"crossref","unstructured":"Schwing, A. G., Hazan, T., Pollefeys, M., & Urtasun, R. (2012). Efficient structured prediction for 3d indoor scene understanding. In 2012 IEEE conference on computer vision and pattern recognition (pp .2815\u20132822). IEEE.","DOI":"10.1109\/CVPR.2012.6248006"},{"key":"1426_CR34","doi-asserted-by":"crossref","unstructured":"Schwing, A. G., & Urtasun, R. (2012). Efficient exact inference for 3d indoor scene understanding. In European conference on computer vision (pp. 299\u2013313). Springer.","DOI":"10.1007\/978-3-642-33783-3_22"},{"key":"1426_CR35","doi-asserted-by":"crossref","unstructured":"Sun, C., Hsiao, C. W., Sun, M., & Chen, H. T. (2019). Horizonnet: Learning room layout with 1d representation and pano stretch data augmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1047\u20131056).","DOI":"10.1109\/CVPR.2019.00114"},{"issue":"4","key":"1426_CR36","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1109\/TPAMI.2008.300","volume":"32","author":"RG Von Gioi","year":"2008","unstructured":"Von Gioi, R. G., Jakubowicz, J., Morel, J. M., & Randall, G. (2008). Lsd: A fast line segment detector with a false detection control. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(4), 722\u2013732.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1426_CR37","unstructured":"Wang, F. E., Yeh, Y. H., Sun, M., Chiu, W. C., & Tsai, Y. H. (2020). Layoutmp3d: Layout annotation of matterport3d. arXiv:2003.13516."},{"key":"1426_CR38","doi-asserted-by":"crossref","unstructured":"Xu, J., Stenger, B., Kerola, T., & Tung, T. (2017). Pano2cad: Room layout from a single panorama image. In 2017 IEEE winter conference on applications of computer vision (WACV) (pp. 354\u2013362). IEEE.","DOI":"10.1109\/WACV.2017.46"},{"key":"1426_CR39","doi-asserted-by":"crossref","unstructured":"Yang, H., & Zhang, H. (2016). Efficient 3d room shape recovery from a single panorama. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5422\u20135430).","DOI":"10.1109\/CVPR.2016.585"},{"key":"1426_CR40","doi-asserted-by":"crossref","unstructured":"Yang, S. T., Peng, C. H., Wonka, P., & Chu, H. K. (2018a). Panoannotator: A semi-automatic tool for indoor panorama layout annotation. In SIGGRAPH Asia 2018 posters (p.\u00a034). ACM.","DOI":"10.1145\/3283289.3283304"},{"key":"1426_CR41","doi-asserted-by":"crossref","unstructured":"Yang, S. T., Wang, F. E., Peng, C. H., Wonka, P., Sun, M., & Chu, H. K. (2019). Dula-net: A dual-projection network for estimating room layouts from a single rgb panorama. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3363\u20133372).","DOI":"10.1109\/CVPR.2019.00348"},{"key":"1426_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Y., Jin, S., Liu, R., Bing\u00a0Kang, S., & Yu, J. (2018b). Automatic 3d indoor scene modeling from single panorama. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00413"},{"key":"1426_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, J., Kan, C., Schwing, A. G., & Urtasun, R. (2013). Estimating the 3d layout of indoor scenes and its clutter from depth sensors. In ICCV (pp. 1273\u20131280).","DOI":"10.1109\/ICCV.2013.161"},{"key":"1426_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Song, S., Tan, P., & Xiao, J. (2014). Panocontext: A whole-room 3d context model for panoramic scene understanding. In European conference on computer vision (pp. 668\u2013686). Springer.","DOI":"10.1007\/978-3-319-10599-4_43"},{"key":"1426_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, H., Lu, M., Yao, A., Guo, Y., Chen, Y., & Zhang, L. (2017). Physics inspired optimization on semantic transfer features: An alternative method for room layout estimation. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.99"},{"key":"1426_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, Y., & Zhu, S. C. (2013). Scene parsing by integrating function, geometry and appearance models. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3119\u20133126).","DOI":"10.1109\/CVPR.2013.401"},{"key":"1426_CR47","doi-asserted-by":"crossref","unstructured":"Zou, C., Colburn, A., Shan, Q., & Hoiem, D. (2018). 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).","DOI":"10.1109\/CVPR.2018.00219"},{"issue":"2","key":"1426_CR48","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s11263-018-1133-z","volume":"127","author":"C Zou","year":"2019","unstructured":"Zou, C., Guo, R., Li, Z., & Hoiem, D. (2019). Complete 3d scene parsing from an rgbd image. International Journal of Computer Vision, 127(2), 143\u2013162.","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01426-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01426-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01426-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T18:12:58Z","timestamp":1620238378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01426-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,9]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["1426"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01426-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,9]]},"assertion":[{"value":"9 October 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}