|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Extracting geometric features from 3D scans or point clouds is the first step in applications such as registration, reconstruction, and tracking.
In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.
Our approach is sensor- and sceneagnostic because of SDV, LRF and learning highly descriptive features with fully convolutional layers.
By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template.
SOTA for 3D Point Cloud Matching on Faust (using extra training data)
Then, the problem of point set registration is reformulated as the problem of aligning two Gaussian mixtures such that a statistical discrepancy measure between the two corresponding mixtures is minimized.