Surface Reconstruction from Silhouette and Laser Scanners as a Positive-Unlabeled Learning Problem

Simple item page
dc.contributor.authorGottardo, Marioen_US
dc.contributor.authorPistellato, Maraen_US
dc.contributor.authorBergamasco, Filippoen_US
dc.contributor.editorCaputo, Arielen_US
dc.contributor.editorGarro, Valeriaen_US
dc.contributor.editorGiachetti, Andreaen_US
dc.contributor.editorCastellani, Umbertoen_US
dc.contributor.editorDulecha, Tinsae Gebrechristosen_US
dc.date.accessioned2024-11-11T12:48:37Z
dc.date.available2024-11-11T12:48:37Z
dc.date.issued2024
dc.description.abstractTypical 3D reconstruction pipelines employ a combination of line-laser scanners and robotic actuators to produce a point cloud and then proceed with surface reconstruction. In this work we propose a new technique to learn an Implicit Neural Representation (INR) of a 3D shape S without directly observing points on its surface. We just assume being able to determine whether a 3D point is exterior to S (e.g. observing if the projection falls outside the silhouette or detecting on which side of the laser line the point is). In this setting, we cast the reconstruction process as a Positive-Unlabelled learning problem where sparse 3D points, sampled according to a distribution depending on the INR's local gradient, have to be classified as being interior or exterior to S. These points, are used to train the INR in an iterative way so that its zero-crossing converges to the boundary of the shape. Preliminary experiments performed on a synthetic dataset demonstrates the advantages of the approach.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationSmart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20241348
dc.identifier.isbn978-3-03868-265-3
dc.identifier.issn2617-4855
dc.identifier.pages3 pages
dc.identifier.urihttps://doi.org/10.2312/stag.20241348
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/stag20241348
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Shape modeling; Shape representations; Reconstruction
dc.subjectComputing methodologies → Shape modeling
dc.subjectShape representations
dc.subjectReconstruction
dc.titleSurface Reconstruction from Silhouette and Laser Scanners as a Positive-Unlabeled Learning Problemen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
stag20241348.pdf
Size:
342.28 KB
Format:
Adobe Portable Document Format
Download
Collections
Italian Chapter Conference 2024 - Smart Tools and Apps in Graphics