Show simple item record

dc.contributor.authorWei, Jianen_US
dc.contributor.authorResch, Benjaminen_US
dc.contributor.authorLensch, Hendrik P. A.en_US
dc.contributor.editorMatthias Hullin and Reinhard Klein and Thomas Schultz and Angela Yaoen_US
dc.date.accessioned2017-09-25T06:55:03Z
dc.date.available2017-09-25T06:55:03Z
dc.date.issued2017
dc.identifier.isbn978-3-03868-049-9
dc.identifier.urihttp://dx.doi.org/10.2312/vmv.20171259
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vmv20171259
dc.description.abstractDepth-map-based multi-view stereo algorithms typically recover textureless surfaces by assuming smoothness per view, so they require processing different views to solve occlusions. Moreover, the highly redundant viewpoints of videos make exhaustive calculation of depth maps unfeasible for large scenes. This paper achieves dense and scalable reconstruction from videos by adaptively selecting a minimum subset of views from the unstructured camera paths, that are most beneficial for incremental occlusion handling and coverage improvement. Furthermore, we simplify and optimize each set of locally consistent points as the points accumulated from a cluster of previously processed views. By combining content-aware view selection and clustering, as well as cluster-wise point merging, our approach can reduce both computational and memory costs while producing accurate, concise, and dense 3D points, even for homogeneous areas. The superior efficiency and point-level fashion of our operations facilitate 3D modeling at large scales.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.4.5 [Image Processing and Computer Vision]
dc.subjectReconstruction
dc.subject
dc.subjectI.3.7 [Computer Graphics]
dc.subjectThree Dimensional Graphics and Realism
dc.subjectColor
dc.subjectShading
dc.subjectShadowing and Texture
dc.titleDense and Scalable Reconstruction from Unstructured Videos with Occlusionsen_US
dc.description.seriesinformationVision, Modeling & Visualization
dc.description.sectionheadersShape Estimation and Analysis
dc.identifier.doi10.2312/vmv.20171259
dc.identifier.pages53-60


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • VMV17
    ISBN 978-3-03868-049-9

Show simple item record