Deep-learning Alignment for Handheld 3D Acquisitions: A new Densematch Dataset for an Extended Comparison

Simple item page
dc.contributor.authorLombardi, Marcoen_US
dc.contributor.authorSavardi, Mattiaen_US
dc.contributor.authorSignoroni, Albertoen_US
dc.contributor.editorBiasotti, Silvia and Pintus, Ruggero and Berretti, Stefanoen_US
dc.date.accessioned2020-11-12T05:42:07Z
dc.date.available2020-11-12T05:42:07Z
dc.date.issued2020
dc.description.abstractPromising solutions for the alignment of 3D views based on representation learning approaches have been proposed very recently. The potentials of these solutions that could positively affect the 3D object registration has yet to be extensively tested. In fact, a direct comparison among advisable technologies is still lacking, especially if the focus is on different data types and real-time application requirements. This work is a first contribution in this direction since we perform an independent extended comparison among prominent deep learning-driven 3D view alignment solutions by considering two relevant setups: 1) data coming from commodity 3D sensors, and 2) denser data coming from a handheld 3D optical scanner. While for the first scenario reference datasets exist, we collect and release the new benchmark dataset DenseMatch for the second setup.en_US
dc.description.sectionheadersAcquisition and Modelling
dc.description.seriesinformationSmart Tools and Apps for Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20201244
dc.identifier.isbn978-3-03868-124-3
dc.identifier.issn2617-4855
dc.identifier.pages101-112
dc.identifier.urihttps://doi.org/10.2312/stag.20201244
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/stag20201244
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectArtificial intelligence
dc.subjectPoint
dc.subjectbased models
dc.subjectHardware
dc.subjectEmerging technologies
dc.titleDeep-learning Alignment for Handheld 3D Acquisitions: A new Densematch Dataset for an Extended Comparisonen_US
Files
Collections
Italian Chapter Conference 2020 - Smart Tools and Apps in computer Graphics