Metadata only
Date
2020-10-01Type
- Journal Article
Citations
Cited 24 times in
Web of Science
Cited 19 times in
Scopus
ETH Bibliography
yes
Altmetrics
Abstract
We address the problem of mesh reconstruction from live RGB-D video, assuming a calibrated camera and poses provided externally (e.g., by a SLAM system). In contrast to most existing approaches, we do not fuse depth measurements in a volume but in a dense surfel cloud. We asynchronously (re)triangulate the smoothed surfels to reconstruct a surface mesh. This novel approach enables to maintain a dense surface representation of the scene during SLAM which can quickly adapt to loop closures. This is possible by deforming the surfel cloud and asynchronously remeshing the surface where necessary. The surfel-based representation also naturally supports strongly varying scan resolution. In particular, it reconstructs colors at the input camera's resolution. Moreover, in contrast to many volumetric approaches, ours can reconstruct thin objects since objects do not need to enclose a volume. We demonstrate our approach in a number of experiments, showing that it produces reconstructions that are competitive with the state-of-the-art, and we discuss its advantages and limitations. The algorithm (excluding loop closure functionality) is available as open source at https://github.com/puzzlepaint/surfelmeshing . Show more
Publication status
publishedExternal links
Journal / series
IEEE Transactions on Pattern Analysis and Machine IntelligenceVolume
Pages / Article No.
Publisher
IEEESubject
3D Modeling and Scene Reconstruction; RGB-D SLAM; Real-Time Dense Mapping; Applications of RGB-D Vision; Depth Fusion; Loop Closure; SurfelsOrganisational unit
03766 - Pollefeys, Marc / Pollefeys, Marc
More
Show all metadata
Citations
Cited 24 times in
Web of Science
Cited 19 times in
Scopus
ETH Bibliography
yes
Altmetrics