2026-07-20T14:34:38Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:1859 2024-03-06T11:08:24Z ddc:004 open_access

Automated Evaluation of 3D Reconstruction Results for Benchmarking View Planning Munkelt, Christoph Denzler, Joachim Next Best View View Planning Optical 3D Reconstruction Benchmarking To obtain complete 3D object reconstructions using optical measurements, several views of the object are necessary. The task of determining good sensor positions to achieve a 3D reconstruction with low error, high completeness and few required views is called the Next Best View (NBV) problem. Solving the NBV problem is an important task for automated 3D reconstruction. However, comparison of different planning methods has been difficult, since only few dedicated test methods exist. We present an extension to our NBV benchmark framework, that allows for faster, automated evaluation of large result data sets. We show that the method introduces insignificant error, while considerably reducing evaluation runtime and increasing robustness. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Christoph Munkelt and Joachim Denzler 2009 Is Part Of Dagstuhl Seminar Proceedings, Volume 8422, Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DagSemProc.08422.6 urn:nbn:de:0030-drops-18596 https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08422.6 eng https://creativecommons.org/licenses/by/4.0/legalcode