{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:05:23Z","timestamp":1760598323591,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729720"},{"type":"electronic","value":"9783031729737"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-72973-7_19","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"322-339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["PolyRoom: Room-Aware Transformer for\u00a0Floorplan Reconstruction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3334-2982","authenticated-orcid":false,"given":"Yuzhou","family":"Liu","sequence":"first","affiliation":[]},{"given":"Lingjie","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Xiaodong","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0313-7085","authenticated-orcid":false,"given":"Hanqiao","family":"Ye","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1497-5637","authenticated-orcid":false,"given":"Xiang","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9783-3030","authenticated-orcid":false,"given":"Xianwei","family":"Zheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8704-7914","authenticated-orcid":false,"given":"Shuhan","family":"Shen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Avetisyan, A., Khanova, T., Choy, C., Dash, D., Dai, A., Nie\u00dfner, M.: SceneCAD: predicting object alignments and layouts in RGB-D scans. In: European Conference on Computer Vision (ECCV), pp. 596\u2013612 (2020)","DOI":"10.1007\/978-3-030-58542-6_36"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Browne, C.B., et al.: A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1\u201343 (2012)","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Cabral, R., Furukawa, Y.: Piecewise planar and compact floorplan reconstruction from images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 628\u2013635 (2014)","DOI":"10.1109\/CVPR.2014.546"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Castrejon, L., Kundu, K., Urtasun, R., Fidler, S.: Annotating object instances with a polygon-RNN. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4485\u20134493 (2017)","DOI":"10.1109\/CVPR.2017.477"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., Wang, R., Vogel, C., Pollefeys, M.: F3Loc: fusion and filtering for floorplan localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18029\u201318038 (2024)","DOI":"10.1109\/CVPR52733.2024.01707"},{"key":"19_CR6","unstructured":"Chen, J., Deng, R., Furukawa, Y.: PolyDiffuse: polygonal shape reconstruction via guided set diffusion models. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 1863\u20131888 (2023)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Liu, C., Wu, J., Furukawa, Y.: Floor-SP: inverse CAD for floorplans by sequential room-wise shortest path. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2661\u20132670 (2019)","DOI":"10.1109\/ICCV.2019.00275"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Qian, Y., Furukawa, Y.: HEAT: holistic edge attention Transformer for structured reconstruction. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3856\u20133865 (2022)","DOI":"10.1109\/CVPR52688.2022.00384"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask Transformer for universal image segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1280\u20131289 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2432\u20132443 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"19_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2020)"},{"issue":"2","key":"19_CR12","doi-asserted-by":"publisher","first-page":"112","DOI":"10.3138\/FM57-6770-U75U-7727","volume":"10","author":"DH Douglas","year":"1973","unstructured":"Douglas, D.H., Peucker, T.K.: Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica 10(2), 112\u2013122 (1973)","journal-title":"Cartographica"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Fan, Z., Zhu, L., Li, H., Chen, X., Zhu, S., Tan, P.: FloorPlanCAD: a large-scale CAD drawing dataset for panoptic symbol spotting. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10108\u201310117 (2021)","DOI":"10.1109\/ICCV48922.2021.00997"},{"issue":"4","key":"19_CR14","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1109\/TPAMI.2018.2890586","volume":"42","author":"JD Favreau","year":"2019","unstructured":"Favreau, J.D., Lafarge, F., Bousseau, A., Auvolat, A.: Extracting geometric structures in images with Delaunay point processes. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 837\u2013850 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR15","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1016\/j.isprsjprs.2023.01.020","volume":"196","author":"J Han","year":"2023","unstructured":"Han, J., Liu, Y., Rong, M., Zheng, X., Shen, S.: FloorUSG: indoor floorplan reconstruction by unifying 2D semantics and 3D geometry. ISPRS J. Photogramm. Remote. Sens. 196, 490\u2013501 (2023)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"19_CR18","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"19_CR19","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.isprsjprs.2023.03.021","volume":"199","author":"Y Hu","year":"2023","unstructured":"Hu, Y., Wang, Z., Huang, Z., Liu, Y.: PolyBuilding: polygon transformer for building extraction. ISPRS J. Photogramm. Remote. Sens. 199, 15\u201327 (2023)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Ibrahem, H., Salem, A., Kang, H.S.: ST-RoomNet: learning room layout estimation from single image through unsupervised spatial transformations. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3376\u20133384 (2023)","DOI":"10.1109\/CVPRW59228.2023.00340"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Ikehata, S., Yang, H., Furukawa, Y.: Structured indoor modeling. In: IEEE International Conference on Computer Vision (ICCV), pp. 1323\u20131331 (2015)","DOI":"10.1109\/ICCV.2015.156"},{"key":"19_CR22","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1644\u20131653 (2022)","DOI":"10.1109\/CVPR52688.2022.00170"},{"key":"19_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Lazarow, J., Xu, W., Tu, Z.: Instance segmentation with mask-supervised polygonal boundary Transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4372\u20134381 (2022)","DOI":"10.1109\/CVPR52688.2022.00434"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Badrinarayanan, V., Malisiewicz, T., Rabinovich, A.: RoomNet: end-to-end room layout estimation. In: IEEE International Conference on Computer Vision (ICCV), pp. 4875\u20134884 (2017)","DOI":"10.1109\/ICCV.2017.521"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Chan, C.L., Le\u00a0Chan, J., Li, Z., Wan, K.W., Yau, W.Y.: Cognitive navigation for indoor environment using floorplan. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9030\u20139037. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9635850"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Liang, J., Homayounfar, N., Ma, W.C., Xiong, Y., Hu, R., Urtasun, R.: PolyTransform: deep polygon transformer for instance segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9128\u20139137 (2020)","DOI":"10.1109\/CVPR42600.2020.00915"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Liao, B., et al.: MapTRv2: an end-to-end framework for online vectorized HD map construction. arXiv preprint arXiv:2308.05736 (2023)","DOI":"10.1007\/s11263-024-02235-z"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Lightweight structured line map based visual localization. IEEE Robot. Automat. Lett. 9(6), 5182\u20135189 (2024)","DOI":"10.1109\/LRA.2024.3387137"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: PolyFormer: referring image segmentation as sequential polygon generation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18653\u201318663 (2023)","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision Transformer using shifted windows. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Peng, S., Jiang, W., Pi, H., Li, X., Bao, H., Zhou, X.: Deep snake for real-time instance segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8530\u20138539 (2020)","DOI":"10.1109\/CVPR42600.2020.00856"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Stekovic, S., Rad, M., Fraundorfer, F., Lepetit, V.: MonteFloor: extending MCTs for reconstructing accurate large-scale floor plans. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16014\u201316023 (2021)","DOI":"10.1109\/ICCV48922.2021.01573"},{"key":"19_CR34","unstructured":"Su, J.W., Tung, K.Y., Peng, C.H., Wonka, P., Chu, H.K.: SLIBO-Net: floorplan reconstruction via slicing box representation with local geometry regularization. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 48781\u201348792 (2023)"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Sun, C., Hsiao, C.W., Sun, M., Chen, H.T.: HorizonNet: learning room layout with 1D representation and pano stretch data augmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1047\u20131056 (2019)","DOI":"10.1109\/CVPR.2019.00114"},{"key":"19_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS) (2017)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Xu, Y., Xu, W., Cheung, D., Tu, Z.: Line segment detection using transformers without edges. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4255\u20134264 (2021)","DOI":"10.1109\/CVPR46437.2021.00424"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Xue, N., et al.: Holistically-attracted wireframe parsing. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2785\u20132794 (2020)","DOI":"10.1109\/CVPR42600.2020.00286"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Yue, Y., Kontogianni, T., Schindler, K., Engelmann, F.: Connecting the dots: floorplan reconstruction using two-level queries. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 845\u2013854 (2023)","DOI":"10.1109\/CVPR52729.2023.00088"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, F., Xu, X., Nauata, N., Furukawa, Y.: Structured outdoor architecture reconstruction by exploration and classification. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12407\u201312415 (2021)","DOI":"10.1109\/ICCV48922.2021.01220"},{"key":"19_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-030-58545-7_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Zheng","year":"2020","unstructured":"Zheng, J., Zhang, J., Li, J., Tang, R., Gao, S., Zhou, Z.: Structured3D: a large photo-realistic dataset for structured 3D modeling. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 519\u2013535. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_30"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Li, J., Zhu, L., Li, H., Petzold, F., Tan, P.: GAT-CADNet: graph attention network for panoptic symbol spotting in CAD drawings. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11737\u201311746 (2022)","DOI":"10.1109\/CVPR52688.2022.01145"},{"key":"19_CR43","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (ICLR) (2020)"}],"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\/978-3-031-72973-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T15:00:33Z","timestamp":1739631633000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72973-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031729720","9783031729737"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72973-7_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}