{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T04:23:22Z","timestamp":1777091002731,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007689","name":"Universidade de Aveiro","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007689","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Reflective surfaces are notoriously difficult to detect and reconstruct, as they reflect light from surrounding objects. Thus, the quality of 3D reconstructions and the performance of downstream computer vision tasks, such as navigation, depth prediction, or object detection are severely impaired by the prevalence of mirrors in indoor environments. This paper proposes a novel reflection-aware method for 3D mirror segmentation and pose estimation, based on the reinterpretation of captured RGB-D data. It is a top-down approach, where information consensus, unsupervised learning, and ray casting are employed, formulating mirror pose estimation as an optimization problem. Experimental results show that the proposed approach significantly outperforms the existing benchmarks for RGB and RGB-D-based 3D mirror segmentation and pose estimation.<\/jats:p>","DOI":"10.1007\/s00371-024-03704-9","type":"journal-article","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T05:45:29Z","timestamp":1732772729000},"page":"5019-5028","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Reflection-aware 3D mirror segmentation and pose estimation"],"prefix":"10.1007","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1335-0803","authenticated-orcid":false,"given":"Tiago","family":"Madeira","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9288-5058","authenticated-orcid":false,"given":"Miguel","family":"Oliveira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3754-2749","authenticated-orcid":false,"given":"Paulo","family":"Dias","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"3704_CR1","doi-asserted-by":"crossref","unstructured":"Lin, J., Wang, G., Lau, R.W.H.: Progressive mirror detection. In: Proceedings CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00375"},{"key":"3704_CR2","doi-asserted-by":"publisher","unstructured":"Chang, A., Dai, A., Funkhouser, T., Halber, M., Niebner, M., Savva, M., Song, S., Zeng, A., Zhang, Y.: Matterport3d: Learning from rgb-d data in indoor environments. In: 2017 International Conference on 3D Vision (3DV), pp. 667\u2013676 (2017). https:\/\/doi.org\/10.1109\/3DV.2017.00081","DOI":"10.1109\/3DV.2017.00081"},{"issue":"4","key":"3704_CR3","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1145\/3197517.3201319","volume":"37","author":"T Whelan","year":"2018","unstructured":"Whelan, T., Goesele, M., Lovegrove, S.J., Straub, J., Green, S., Szeliski, R., Butterfield, S., Verma, S., Newcombe, R.: Reconstructing scenes with mirror and glass surfaces. ACM Trans. Graphic. (TOG) 37(4), 102 (2018)","journal-title":"ACM Trans. Graphic. (TOG)"},{"key":"3704_CR4","doi-asserted-by":"publisher","unstructured":"Pang, Y., Zhao, X., Zhang, L., Lu, H.: Multi-scale interactive network for salient object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9410\u20139419 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00943","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"3704_CR5","doi-asserted-by":"publisher","unstructured":"Zhang, M., Ren, W., Piao, Y., Rong, Z., Lu, H.: Select, supplement and focus for rgb-d saliency detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3469\u20133478 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00353","DOI":"10.1109\/CVPR42600.2020.00353"},{"key":"3704_CR6","doi-asserted-by":"publisher","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: Criss-cross attention for semantic segmentation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 603\u2013612 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00069","DOI":"10.1109\/ICCV.2019.00069"},{"key":"3704_CR7","doi-asserted-by":"publisher","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6230\u20136239 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"3704_CR8","doi-asserted-by":"crossref","unstructured":"Yang, X., Mei, H., Xu, K., Wei, X., Yin, B., Lau, R.W.H.: Where is my mirror? In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00890"},{"key":"3704_CR9","doi-asserted-by":"publisher","unstructured":"Tan, J., Lin, W., Chang, A.X., Savva, M.: Mirror3d: Depth refinement for mirror surfaces. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15985\u201315994 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01573","DOI":"10.1109\/CVPR46437.2021.01573"},{"key":"3704_CR10","doi-asserted-by":"publisher","unstructured":"Yang, S.-W., Wang, C.-C.: Dealing with laser scanner failure: Mirrors and windows. In: 2008 IEEE International Conference on Robotics and Automation, pp. 3009\u20133015 (2008). https:\/\/doi.org\/10.1109\/ROBOT.2008.4543667","DOI":"10.1109\/ROBOT.2008.4543667"},{"key":"3704_CR11","doi-asserted-by":"publisher","unstructured":"K\u00e4shammer, P.-F., N\u00fcchter, A.: Mirror Identification and Correction of 3d Point Clouds. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL5, 109\u2013114 (2015). https:\/\/doi.org\/10.5194\/isprsarchives-XL-5-W4-109-2015","DOI":"10.5194\/isprsarchives-XL-5-W4-109-2015"},{"key":"3704_CR12","doi-asserted-by":"publisher","unstructured":"Balzer, J., Hofer, S., Beyerer, J.: Multiview specular stereo reconstruction of large mirror surfaces. In: CVPR 2011, pp. 2537\u20132544 (2011). https:\/\/doi.org\/10.1109\/CVPR.2011.5995346","DOI":"10.1109\/CVPR.2011.5995346"},{"key":"3704_CR13","doi-asserted-by":"publisher","unstructured":"Balzer, J., Acevedo-Feliz, D., Soatto, S., H\u00f6fer, S., Hadwiger, M., Beyerer, J.: Cavlectometry: Towards holistic reconstruction of large mirror objects. In: 2014 2nd International Conference on 3D Vision, vol. 1, pp. 448\u2013455 (2014). https:\/\/doi.org\/10.1109\/3DV.2014.85","DOI":"10.1109\/3DV.2014.85"},{"issue":"4","key":"3704_CR14","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1109\/TPAMI.2014.2353622","volume":"37","author":"M Liu","year":"2015","unstructured":"Liu, M., Hartley, R., Salzmann, M.: Mirror surface reconstruction from a single image. IEEE Trans. Pattern Anal. Mach. Intell 37(4), 760\u2013773 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2014.2353622","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"3704_CR15","doi-asserted-by":"publisher","unstructured":"Olson, E.: Apriltag: A robust and flexible visual fiducial system. In: 2011 IEEE International Conference on Robotics and Automation, pp. 3400\u20133407 (2011). https:\/\/doi.org\/10.1109\/ICRA.2011.5979561","DOI":"10.1109\/ICRA.2011.5979561"},{"key":"3704_CR16","doi-asserted-by":"crossref","unstructured":"He, R., Lin, J., Lau, R.W.: Efficient mirror detection via multi-level heterogeneous learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 790\u2013798 (2023)","DOI":"10.1609\/aaai.v37i1.25157"},{"issue":"3","key":"3704_CR17","doi-asserted-by":"publisher","first-page":"3492","DOI":"10.1109\/TPAMI.2022.3181030","volume":"45","author":"X Tan","year":"2023","unstructured":"Tan, X., Lin, J., Xu, K., Chen, P., Ma, L., Lau, R.W.H.: Mirror detection with the visual chirality cue. IEEE Trans. Pattern Anal. Machine Intell 45(3), 3492\u20133504 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3181030","journal-title":"IEEE Trans. Pattern Anal. Machine Intell"},{"issue":"6","key":"3704_CR18","doi-asserted-by":"publisher","first-page":"6315","DOI":"10.1609\/aaai.v38i6.28450","volume":"38","author":"K Xu","year":"2024","unstructured":"Xu, K., Siu, T.W., Lau, R.W.H.: Zoom: learning video mirror detection with extremely-weak supervision. Proceed. AAAI Confer. Artific. Intell 38(6), 6315\u20136323 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i6.28450","journal-title":"Proceed. AAAI Confer. Artific. Intell"},{"key":"3704_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103701","volume":"136","author":"R de Queiroz Mendes","year":"2021","unstructured":"de Queiroz Mendes, R., Ribeiro, E.G., dos Santos Rosa, N., Grassi, V.: On deep learning techniques to boost monocular depth estimation for autonomous navigation. Robot. Autonomous Syst. 136, 103701 (2021). https:\/\/doi.org\/10.1016\/j.robot.2020.103701","journal-title":"Robot. Autonomous Syst."},{"key":"3704_CR20","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/978-3-030-58601-0_8","volume-title":"Comput. Vision - ECCV 2020","author":"J Park","year":"2020","unstructured":"Park, J., Joo, K., Hu, Z., Liu, C.-K., So Kweon, I.: Non-local spatial propagation network for depth completion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Comput. Vision - ECCV 2020, pp. 120\u2013136. Springer, Cham (2020)"},{"key":"3704_CR21","doi-asserted-by":"crossref","unstructured":"Senushkin, D., Belikov, I., Konushin, A.: Decoder modulation for indoor depth completion. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2181\u20132188 (2020)","DOI":"10.1109\/IROS51168.2021.9636870"},{"key":"3704_CR22","doi-asserted-by":"publisher","unstructured":"Huang, Y.-K., Wu, T.-H., Liu, Y.-C., Hsu, W.H.: Indoor depth completion with boundary consistency and self-attention. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 1070\u20131078 (2019). https:\/\/doi.org\/10.1109\/ICCVW.2019.00137","DOI":"10.1109\/ICCVW.2019.00137"},{"key":"3704_CR23","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Funkhouser, T.: Deep depth completion of a single rgb-d image. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 175\u2013185. IEEE Computer Society, Los Alamitos, CA, USA (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00026","DOI":"10.1109\/CVPR.2018.00026"},{"key":"3704_CR24","doi-asserted-by":"publisher","unstructured":"Chabra, R., Straub, J., Sweeney, C., Newcombe, R., Fuchs, H.: Stereodrnet: Dilated residual stereonet. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11778\u201311787. IEEE Computer Society, Los Alamitos, CA, USA (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01206","DOI":"10.1109\/CVPR.2019.01206"},{"key":"3704_CR25","unstructured":"Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining. KDD\u201996, pp. 226\u2013231. AAAI Press, (1996)"},{"key":"3704_CR26","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-642-37456-2_14","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"RJGB Campello","year":"2013","unstructured":"Campello, R.J.G.B., Moulavi, D., Sander, J.: Density-based clustering based on hierarchical density estimates. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds.) Advances in Knowledge Discovery and Data Mining, pp. 160\u2013172. Springer, Berlin, Heidelberg (2013)"},{"key":"3704_CR27","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/s10618-013-0311-4","volume":"27","author":"RJ Campello","year":"2013","unstructured":"Campello, R.J., Moulavi, D., Zimek, A., Sander, J.: A framework for semi-supervised and unsupervised optimal extraction of clusters from hierarchies. Data Min. Knowledge Discover. 27, 344\u2013371 (2013)","journal-title":"Data Min. Knowledge Discover."},{"issue":"6","key":"3704_CR28","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981). https:\/\/doi.org\/10.1145\/358669.358692","journal-title":"Commun. ACM"},{"key":"3704_CR29","doi-asserted-by":"publisher","unstructured":"Rusu, R.B., Blodow, N., Beetz, M.: Fast point feature histograms (fpfh) for 3d registration. In: 2009 IEEE International Conference on Robotics and Automation, pp. 3212\u20133217 (2009). https:\/\/doi.org\/10.1109\/ROBOT.2009.5152473","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"3704_CR30","doi-asserted-by":"publisher","unstructured":"Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597\u20131604 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206596","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"3704_CR31","doi-asserted-by":"publisher","unstructured":"Liu, C., Kim, K., Gu, J., Furukawa, Y., Kautz, J.: Planercnn: 3d plane detection and reconstruction from a single image. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4445\u20134454 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00458","DOI":"10.1109\/CVPR.2019.00458"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03704-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03704-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03704-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T10:03:51Z","timestamp":1745489031000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03704-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"references-count":31,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["3704"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03704-9","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"25 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}