Point cloud geometry is cast as a statistical manifold of per-point Gaussians, with POLI learning the mapping self-supervisedly to improve perception without labeled data.
URL https:// link.springer.com/article/10.1007/s11263-013-0627-y
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Point Cloud Geometry as a Statistical Manifold: Theory and Practice
Point cloud geometry is cast as a statistical manifold of per-point Gaussians, with POLI learning the mapping self-supervisedly to improve perception without labeled data.