{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T21:35:27Z","timestamp":1774733727362,"version":"3.50.1"},"reference-count":50,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T00:00:00Z","timestamp":1602115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Structure from Motion (SfM) can produce highly detailed 3D reconstructions, but distinguishing real surface roughness from reconstruction noise and geometric inaccuracies has always been a difficult problem to solve. Existing SfM commercial solutions achieve noise removal by a combination of aggressive global smoothing and the reconstructed texture for smaller details, which is a subpar solution when the results are used for surface inspection. Other noise estimation and removal algorithms do not take advantage of all the additional data connected with SfM. We propose a number of geometrical and statistical metrics for noise assessment, based on both the reconstructed object and the capturing camera setup. We test the correlation of each of the metrics to the presence of noise on reconstructed surfaces and demonstrate that classical supervised learning methods, trained with these metrics can be used to distinguish between noise and roughness with an accuracy above 85%, with an additional 5\u20136% performance coming from the capturing setup metrics. Our proposed solution can easily be integrated into existing SfM workflows as it does not require more image data or additional sensors. Finally, as part of the testing we create an image dataset for SfM from a number of objects with varying shapes and sizes, which are available online together with ground truth annotations.<\/jats:p>","DOI":"10.3390\/s20195725","type":"journal-article","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T10:19:23Z","timestamp":1602238763000},"page":"5725","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Rough or Noisy? Metrics for Noise Estimation in SfM Reconstructions"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-8848","authenticated-orcid":false,"given":"Ivan","family":"Nikolov","sequence":"first","affiliation":[{"name":"Department of Architecture, Design and Media Technology, Aalborg University, Rendsburggade 14, DK-9000 Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0762-3713","authenticated-orcid":false,"given":"Claus","family":"Madsen","sequence":"additional","affiliation":[{"name":"Department of Architecture, Design and Media Technology, Aalborg University, Rendsburggade 14, DK-9000 Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.autcon.2014.01.004","article-title":"Mobile 3D mapping for surveying earthwork projects using an Unmanned Aerial Vehicle (UAV) system","volume":"41","author":"Siebert","year":"2014","journal-title":"Autom. Constr."},{"key":"ref_2","first-page":"3","article-title":"Acquisition and consecutive registration of photogrammetric point clouds for construction progress monitoring using a 4D BIM","volume":"85","author":"Tuttas","year":"2017","journal-title":"PFG J. Photogramm. Remote Sens. Geoinf. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chaiyasarn, K., Kim, T.K., Viola, F., Cipolla, R., and Soga, K. (2015). Distortion-free image mosaicing for tunnel inspection based on robust cylindrical surface estimation through structure from motion. J. Comput. Civ. Eng., 30.","DOI":"10.1061\/(ASCE)CP.1943-5487.0000516"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Khaloo, A., and Lattanzi, D. (2016). Hierarchical dense structure-from-motion reconstructions for infrastructure condition assessment. J. Comput. Civ. Eng., 31.","DOI":"10.1061\/(ASCE)CP.1943-5487.0000616"},{"key":"ref_5","unstructured":"Zhang, D., Burnham, K., Mcdonald, L., Macleod, C., Dobie, G., Summan, R., and Pierce, G. (2017, January 4\u20137). Remote inspection of wind turbine blades using UAV with photogrammetry payload. Proceedings of the 56th Annual British Conference of Non-Destructive Testing-NDT 2017, Telford, UK."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.jsg.2014.10.007","article-title":"Ground-based and UAV-based photogrammetry: A multi-scale, high-resolution mapping tool for structural geology and paleoseismology","volume":"69","author":"Bemis","year":"2014","journal-title":"J. Struct. Geol."},{"key":"ref_7","unstructured":"Cho, Y., and Clary, R. (2017, January 23\u201324). Application of SfM-MVS Photogrammetry in Geology Virtual Field Trips. Proceedings of the 81st Annual Meeting of Mississippi Academy Sciences, Hattiesburg, MS, USA."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2495","DOI":"10.1080\/01431161.2016.1249308","article-title":"Using an unmanned aerial vehicle for topography mapping of the fault zone based on structure from motion photogrammetry","volume":"38","author":"Bi","year":"2017","journal-title":"Int. J. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kersten, T.P., and Lindstaedt, M. (2012). Image-based low-cost systems for automatic 3D recording and modelling of archaeological finds and objects. Euro-Mediterranean Conference, Springer.","DOI":"10.1007\/978-3-642-34234-9_1"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1260\/2047-4970.3.2.431","article-title":"4D reconstruction of tangible cultural heritage objects from web-retrieved images","volume":"3","author":"Kyriakaki","year":"2014","journal-title":"Int. J. Herit. Digit. Era"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1017\/aap.2017.28","article-title":"Using Structure from Motion mapping to record and analyze details of the Colossal Hats (Pukao) of monumental statues on Rapa Nui (Easter Island)","volume":"6","author":"Hixon","year":"2018","journal-title":"Adv. Archaeol. Pract."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"573","DOI":"10.5194\/isprsarchives-XL-5-573-2014","article-title":"A comparison of multi-view 3D reconstruction of a rock wall using several cameras and a laser scanner","volume":"40","author":"Thoeni","year":"2014","journal-title":"Int. Arch. Photogramm. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sch\u00f6ning, J., and Heidemann, G. (2015). Evaluation of multi-view 3D reconstruction software. International Conference on Computer Analysis of Images and Patterns, Springer.","DOI":"10.1007\/978-3-319-23117-4_39"},{"key":"ref_14","unstructured":"Nikolov, I., and Madsen, C. (November, January 31). Benchmarking close-range structure from motion 3D reconstruction software under varying capturing conditions. Proceedings of the Euro-Mediterranean Conference Conference, Nicosia, Cyprus."},{"key":"ref_15","unstructured":"Agisoft (2019, September 20). Metashape. Available online: http:\/\/www.agisoft.com\/."},{"key":"ref_16","unstructured":"Bentley (2019, September 20). ContextCapture. Available online: https:\/\/www.bentley.com\/."},{"key":"ref_17","unstructured":"CapturingReality (2019, September 20). Reality Capture. Available online: https:\/\/www.capturingreality.com\/."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1111\/j.1467-8659.2005.00854.x","article-title":"Geofilter: Geometric selection of mesh filter parameters","volume":"Volume 24","author":"Kim","year":"2005","journal-title":"Computer Graphics Forum"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Nealen, A., Igarashi, T., Sorkine, O., and Alexa, M. (December, January 29). Laplacian mesh optimization. Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia 2006, Kuala Lumpur, Malaysia.","DOI":"10.1145\/1174429.1174494"},{"key":"ref_20","unstructured":"Su, Z.X., Wang, H., and Cao, J.J. (2009, January 26\u201328). Mesh denoising based on differential coordinates. Proceedings of the 2009 IEEE International Conference on Shape Modeling and Applications, Beijing, China."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.cagd.2017.02.011","article-title":"Robust mesh denoising via vertex pre-filtering and l1-median normal filtering","volume":"54","author":"Lu","year":"2017","journal-title":"Comput. Aided Geom. Des."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1145\/2980179.2980232","article-title":"Mesh denoising via cascaded normal regression","volume":"35","author":"Wang","year":"2016","journal-title":"ACM Trans. Graph."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.optlaseng.2016.09.003","article-title":"An efficient approach for feature-preserving mesh denoising","volume":"90","author":"Lu","year":"2017","journal-title":"Opt. Lasers Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1109\/TVCG.2010.264","article-title":"Bilateral normal filtering for mesh denoising","volume":"17","author":"Zheng","year":"2010","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_25","first-page":"27","article-title":"Joint bilateral mesh denoising using color information and local anti-shrinking","volume":"23","author":"Bleser","year":"2015","journal-title":"J. Wscg."},{"key":"ref_26","first-page":"21","article-title":"A local roughness measure for 3D meshes and its application to visual masking","volume":"5","year":"2009","journal-title":"ACM Trans. Appl. Percept."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1016\/j.cag.2012.06.004","article-title":"A fast roughness-based approach to the assessment of 3D mesh visual quality","volume":"36","author":"Wang","year":"2012","journal-title":"Comput. Graph."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1145\/2530691","article-title":"Mesh saliency via spectral processing","volume":"33","author":"Song","year":"2014","journal-title":"ACM Trans. Graph."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Guo, J., Vidal, V., Baskurt, A., and Lavou\u00e9, G. (2015, January 13\u201314). Evaluating the local visibility of geometric artifacts. Proceedings of the ACM SIGGRAPH Symposium on Applied Perception, T\u00fcbingen, Germany.","DOI":"10.1145\/2804408.2804418"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ioannou, Y., Taati, B., Harrap, R., and Greenspan, M. (2012, January 13\u201315). Difference of normals as a multi-scale operator in unorganized point clouds. Proceedings of the 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission, Zurich, Switzerland.","DOI":"10.1109\/3DIMPVT.2012.12"},{"key":"ref_31","first-page":"248","article-title":"Segmentation of point clouds using smoothness constraint","volume":"36","author":"Rabbani","year":"2006","journal-title":"Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.3390\/rs4061573","article-title":"Assessing the accuracy of georeferenced point clouds produced via multi-view stereopsis from unmanned aerial vehicle (UAV) imagery","volume":"4","author":"Harwin","year":"2012","journal-title":"Remote. Sens."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Huhle, B., Schairer, T., Jenke, P., and Stra\u00dfer, W. (2008, January 23\u201328). Robust non-local denoising of colored depth data. Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Anchorage, AK, USA.","DOI":"10.1109\/CVPRW.2008.4563158"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0734-189X(86)80025-1","article-title":"Edge extraction using entropy operator","volume":"36","author":"Shiozaki","year":"1986","journal-title":"Comput. Vision Graph. Image Process."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.cageo.2011.09.012","article-title":"Multiview 3D reconstruction in geosciences","volume":"44","author":"Favalli","year":"2012","journal-title":"Comput. Geosci."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"D\u2019Amico, N., and Yu, T. (2017, January 25\u201329). Accuracy analysis of point cloud modeling for evaluating concrete specimens. Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2017. In Proceedings of the International Society for Optics and Photonics, San Diego, CA, USA.","DOI":"10.1117\/12.2258404"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1017\/S096249291700006X","article-title":"A survey of structure from motion*","volume":"26","author":"Voroninski","year":"2017","journal-title":"Acta Numer."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., and van Gool, L. (2006). Surf: Speeded up robust features. European Conference on Computer Vision, Springer.","DOI":"10.1007\/11744023_32"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Rosten, E., and Drummond, T. (2006). Machine learning for high-speed corner detection. European Conference on Computer Vision, Springer.","DOI":"10.1007\/11744023_34"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011, January 6\u201313). ORB: An efficient alternative to SIFT or SURF. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref_41","unstructured":"Kodak (1969). Optical Formulas and Their Applications, Kodak."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"13","DOI":"10.2478\/sjce-2013-0017","article-title":"Quality of 3D models generated by SFM technology","volume":"21","year":"2013","journal-title":"Slovak J.Civ. Eng."},{"key":"ref_43","unstructured":"Zhou, Q.Y., Park, J., and Koltun, V. (2018). Open3D: A Modern Library for 3D Data Processing. arXiv."},{"key":"ref_44","first-page":"120","article-title":"The OpenCV Library","volume":"25","author":"Bradski","year":"2000","journal-title":"J. Softw. Tools"},{"key":"ref_45","unstructured":"Technologies, U. (2020, July 20). Unity. Available online: unity.com."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Benesty, J., Chen, J., Huang, Y., and Cohen, I. (2009). Pearson correlation coefficient. Noise Reduction in Speech Processing, Springer.","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"ref_47","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Zhang, D., Watson, R., Dobie, G., MacLeod, C., Khan, A., and Pierce, G. (2020). Quantifying impacts on remote photogrammetric inspection using unmanned aerial vehicles. Eng. Struct., 209.","DOI":"10.1016\/j.engstruct.2019.109940"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Saito, T., and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0118432"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/19\/5725\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:17:38Z","timestamp":1760177858000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/19\/5725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,8]]},"references-count":50,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["s20195725"],"URL":"https:\/\/doi.org\/10.3390\/s20195725","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,8]]}}}