Depth Map Repairing for Building Reconstruction

dc.contributor.authorAndújar, Carlosen_US
dc.contributor.authorArgudo, Oscaren_US
dc.contributor.authorBesora, Isaacen_US
dc.contributor.authorBrunet, Pereen_US
dc.contributor.authorChica, Antonien_US
dc.contributor.authorComino Trinidad, Marcen_US
dc.contributor.editorGarcía-Fernández, Ignacio and Ureña, Carlosen_US
dc.date.accessioned2018-06-26T13:59:37Z
dc.date.available2018-06-26T13:59:37Z
dc.date.issued2018
dc.description.abstractStructure-from-motion along with multi-view stereo techniques jointly allow for the inexpensive scanning of 3D objects (e.g. buildings) using just a collection of images taken from commodity cameras. Despite major advances in these fields, a major limitation of dense reconstruction algorithms is that correct depth/normal values are not recovered on specular surfaces (e.g. windows) and parts lacking image features (e.g. flat, textureless parts of the facade). Since these reflective properties are inherent to the surface being acquired, images from different viewpoints hardly contribute to solve this problem. In this paper we present a simple method for detecting, classifying and filling non-valid data regions in depth maps produced by dense stereo algorithms. Triangles meshes reconstructed from our repaired depth maps exhibit much higher quality than those produced by state-of-the-art reconstruction algorithms like Screened Poisson-based techniques.en_US
dc.description.sectionheadersProcedural Modelling and Models Acquisition
dc.description.seriesinformationSpanish Computer Graphics Conference (CEIG)
dc.identifier.doi10.2312/ceig.20181162
dc.identifier.isbn978-3-03868-067-3
dc.identifier.pages95-102
dc.identifier.urihttps://doi.org/10.2312/ceig.20181162
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/ceig20181162
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectComputer graphics
dc.titleDepth Map Repairing for Building Reconstructionen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
095-102.pdf
Size:
10.4 MB
Format:
Adobe Portable Document Format
Collections