UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration. (arXiv:2208.02712v5 [cs.CV] UPDATED)

High-confidence overlap prediction and accurate correspondences are critical
for cutting-edge models to align paired point clouds in a partial-to-partial
manner. However, there inherently exists uncertainty between the overlapping
and non-overlapping regions, which has always been neglected and significantly
affects the registration performance. Beyond the current wisdom, we propose a
novel uncertainty-aware overlap prediction network, dubbed UTOPIC, to tackle
the ambiguous overlap prediction problem; to our knowledge, this is the first
to explicitly introduce overlap uncertainty to point cloud registration.
Moreover, …

arxiv cloud network prediction registration uncertainty