Bayesian 3D Shape Reconstruction from Noisy Points and Normals

dc.contributor.authorPujol, Eduarden_US
dc.contributor.authorChica, Antonioen_US
dc.contributor.editorAttene, Marcoen_US
dc.contributor.editorSellán, Silviaen_US
dc.date.accessioned2025-06-20T07:40:37Z
dc.date.available2025-06-20T07:40:37Z
dc.date.issued2025
dc.description.abstractReconstructing three-dimensional shapes from point clouds remains a central challenge in geometry processing, particularly due to the inherent uncertainties in real-world data acquisition. In this work, we introduce a novel Bayesian framework that explicitly models and propagates uncertainty from both input points and their estimated normals. Our method incorporates the uncertainty of normals derived via Principal Component Analysis (PCA) from noisy input points. Building upon the Smooth Signed Distance (SSD) reconstruction algorithm, we integrate a smoothness prior based on the curvatures of the resulting implicit function following Gaussian behavior. Our method reconstructs a shape represented as a distribution, from which sampling and statistical queries regarding the shape's properties are possible. Additionally, because of the high cost of computing the variance of the resulting distribution, we develop efficient techniques for variance computation. Our approach thus combines two common steps of the geometry processing pipeline, normal estimation and surface reconstruction, while computing the uncertainty of the output of each of these steps.en_US
dc.description.number5
dc.description.sectionheadersReconstruction
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70201
dc.identifier.issn1467-8659
dc.identifier.pages14 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70201
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70201
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Computer graphics
dc.subjectComputing methodologies → Computer graphics
dc.titleBayesian 3D Shape Reconstruction from Noisy Points and Normalsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
cgf70201.pdf
Size:
64.71 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
fp2-1056_mm.pdf
Size:
132.67 MB
Format:
Adobe Portable Document Format
Collections