{"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":1771961005882,"version":"3.50.1"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100009873","name":"Regione Autonoma della Sardegna","doi-asserted-by":"publisher","award":["VIGECLAB"],"award-info":[{"award-number":["VIGECLAB"]}],"id":[{"id":"10.13039\/501100009873","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["813170"],"award-info":[{"award-number":["813170"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:p>Recovering the 3D shape of the bounding permanent surfaces of a room from a single image is a key component of indoor reconstruction pipelines. In this article, we introduce a novel deep learning technique capable to produce, at interactive rates, a tessellated bounding 3D surface from a single 360\u00b0 image. Differently from prior solutions, we fully address the problem in 3D, significantly expanding the reconstruction space of prior solutions. A graph convolutional network directly infers the room structure as a 3D mesh by progressively deforming a graph-encoded tessellated sphere mapped to the spherical panorama, leveraging perceptual features extracted from the input image. Important 3D properties of indoor environments are exploited in our design. In particular, gravity-aligned features are actively incorporated in the graph in a projection layer that exploits the recent concept of multi head self-attention, and specialized losses guide towards plausible solutions even in presence of massive clutter and occlusions. Extensive experiments demonstrate that our approach outperforms current state of the art methods in terms of accuracy and capability to reconstruct more complex environments.<\/jats:p>","DOI":"10.1145\/3478513.3480480","type":"journal-article","created":{"date-parts":[[2021,12,10]],"date-time":"2021-12-10T18:28:45Z","timestamp":1639160925000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Deep3DLayout"],"prefix":"10.1145","volume":"40","author":[{"given":"Giovanni","family":"Pintore","sequence":"first","affiliation":[{"name":"CRS4, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eva","family":"Almansa","sequence":"additional","affiliation":[{"name":"CRS4, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Agus","sequence":"additional","affiliation":[{"name":"HBKU, Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Gobbetti","sequence":"additional","affiliation":[{"name":"CRS4, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,12,10]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00365"},{"key":"e_1_2_1_2_1","volume-title":"Henriques","author":"Davidson Benjamin","year":"2020","unstructured":"Benjamin Davidson , Mohsan S. Alvi , and Joao F . Henriques . 2020 . 360 Camera Alignment via Segmentation. In Proc. ECCV. 579--595. Benjamin Davidson, Mohsan S. Alvi, and Joao F. Henriques. 2020. 360 Camera Alignment via Segmentation. In Proc. ECCV. 579--595."},{"key":"e_1_2_1_3_1","unstructured":"Dawson-Haggerty et al. 2019. trimesh. https:\/\/trimesh.org\/  Dawson-Haggerty et al. 2019. trimesh. https:\/\/trimesh.org\/"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888150.1888182"},{"key":"e_1_2_1_5_1","volume-title":"Mesh R-CNN. In Proc. ICCV. 9784--9794","author":"Gkioxari G.","unstructured":"G. Gkioxari , J. Johnson , and J. Malik . 2019 . Mesh R-CNN. In Proc. ICCV. 9784--9794 . G. Gkioxari, J. Johnson, and J. Malik. 2019. Mesh R-CNN. In Proc. ICCV. 9784--9794."},{"key":"e_1_2_1_6_1","volume-title":"Proc. CVPR. 770--778","author":"He K.","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun . 2016. Deep Residual Learning for Image Recognition . In Proc. CVPR. 770--778 . K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep Residual Learning for Image Recognition. In Proc. CVPR. 770--778."},{"key":"e_1_2_1_7_1","volume-title":"Proc. ICCV. 1849--1856","author":"Hedau V.","unstructured":"V. Hedau , D. Hoiem , and D. Forsyth . 2009. Recovering the spatial layout of cluttered rooms . In Proc. ICCV. 1849--1856 . V. Hedau, D. Hoiem, and D. Forsyth. 2009. Recovering the spatial layout of cluttered rooms. In Proc. ICCV. 1849--1856."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0031-y"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2019.8798326"},{"key":"e_1_2_1_10_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A Method for Stochastic Optimization. ArXiv e-print arXiv:1412.6980 (2014). Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. ArXiv e-print arXiv:1412.6980 (2014)."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206872"},{"key":"e_1_2_1_13_1","unstructured":"Matterport. 2017. Matterport3D. https:\/\/github.com\/niessner\/Matterport. [Accessed: 2019-09-25].  Matterport. 2017. Matterport3D. https:\/\/github.com\/niessner\/Matterport. [Accessed: 2019-09-25]."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073645"},{"key":"e_1_2_1_15_1","volume-title":"Barr","author":"Meyer Mark","year":"2003","unstructured":"Mark Meyer , Mathieu Desbrun , Peter Schr\u00f6der , and Alan H . Barr . 2003 . Discrete Differential-Geometry Operators for Triangulated 2-Manifolds. In Visualization and Mathematics III. 35--57. Mark Meyer, Mathieu Desbrun, Peter Schr\u00f6der, and Alan H. Barr. 2003. Discrete Differential-Geometry Operators for Triangulated 2-Manifolds. In Visualization and Mathematics III. 35--57."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4438750"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_25"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073324"},{"key":"e_1_2_1_19_1","volume-title":"Proc. NIPS Workshop on Autodiff.","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke , Sam Gross , Soumith Chintala , Gregory Chanan , Edward Yang , Zachary DeVito , Zeming Lin , Alban Desmaison , Luca Antiga , and Adam Lerer . 2017 . Automatic differentiation in PyTorch . In Proc. NIPS Workshop on Autodiff. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in PyTorch. In Proc. NIPS Workshop on Autodiff."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01137"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_26"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14021"},{"key":"e_1_2_1_23_1","volume-title":"Accelerating 3D Deep Learning with Py-Torch3D. arXiv preprint arXiv:2007.08501","author":"Ravi Nikhila","year":"2020","unstructured":"Nikhila Ravi , Jeremy Reizenstein , David Novotny , Taylor Gordon , Wan-Yen Lo , Justin Johnson , and Georgia Gkioxari . 2020. Accelerating 3D Deep Learning with Py-Torch3D. arXiv preprint arXiv:2007.08501 ( 2020 ). Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari. 2020. Accelerating 3D Deep Learning with Py-Torch3D. arXiv preprint arXiv:2007.08501 (2020)."},{"key":"e_1_2_1_24_1","volume-title":"Proc. ICML. 5866--5876","author":"Smith Edward","year":"2019","unstructured":"Edward Smith , Scott Fujimoto , Adriana Romero , and David Meger . 2019 . GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects . In Proc. ICML. 5866--5876 . Edward Smith, Scott Fujimoto, Adriana Romero, and David Meger. 2019. GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects. In Proc. ICML. 5866--5876."},{"key":"e_1_2_1_25_1","unstructured":"Stanford University. 2017. BuildingParser Dataset. http:\/\/buildingparser.stanford.edu\/dataset.html. [Accessed: 2019-09-25].  Stanford University. 2017. BuildingParser Dataset. http:\/\/buildingparser.stanford.edu\/dataset.html. [Accessed: 2019-09-25]."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00114"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00260"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00054"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01276"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01007"},{"key":"e_1_2_1_33_1","volume-title":"Proc. WACV. 354--362","author":"Xu J.","unstructured":"J. Xu , B. Stenger , T. Kerola , and T. Tung . 2017. Pano2CAD: Room Layout from a Single Panorama Image . In Proc. WACV. 354--362 . J. Xu, B. Stenger, T. Kerola, and T. Tung. 2017. Pano2CAD: Room Layout from a Single Panorama Image. In Proc. WACV. 354--362."},{"key":"e_1_2_1_34_1","volume-title":"Proc. CVPR. 5422--5430","author":"Yang H.","unstructured":"H. Yang and H. Zhang . 2016. Efficient 3D Room Shape Recovery from a Single Panorama . In Proc. CVPR. 5422--5430 . H. Yang and H. Zhang. 2016. Efficient 3D Room Shape Recovery from a Single Panorama. In Proc. CVPR. 5422--5430."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3389412"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00348"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_39"},{"key":"e_1_2_1_38_1","volume-title":"Proc. ICML. 7354--7363","author":"Zhang Han","year":"2019","unstructured":"Han Zhang , Ian Goodfellow , Dimitris Metaxas , and Augustus Odena . 2019 . Self-attention generative adversarial networks . In Proc. ICML. 7354--7363 . Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena. 2019. Self-attention generative adversarial networks. In Proc. ICML. 7354--7363."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_43"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00081"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_28"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00219"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01426-8"},{"key":"e_1_2_1_45_1","volume-title":"3D Manhattan Room Layout Reconstruction from a Single 360 Image. ArXiv e-print arXiv:1910.04099","author":"Zou Chuhang","year":"2019","unstructured":"Chuhang Zou , Jheng-Wei Su , Chi-Han Peng , Alex Colburn , Qi Shan , Peter Wonka , Hung-Kuo Chu , and Derek Hoiem . 2019. 3D Manhattan Room Layout Reconstruction from a Single 360 Image. ArXiv e-print arXiv:1910.04099 ( 2019 ). Chuhang Zou, Jheng-Wei Su, Chi-Han Peng, Alex Colburn, Qi Shan, Peter Wonka, Hung-Kuo Chu, and Derek Hoiem. 2019. 3D Manhattan Room Layout Reconstruction from a Single 360 Image. ArXiv e-print arXiv:1910.04099 (2019)."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3478513.3480480","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3478513.3480480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:48Z","timestamp":1750191108000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3478513.3480480"}},"subtitle":["3D reconstruction of an indoor layout from a spherical panoramic image"],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":45,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["10.1145\/3478513.3480480"],"URL":"https:\/\/doi.org\/10.1145\/3478513.3480480","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"2021-12-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}