FLAT embeds rotation- and translation-invariant cross-cloud geometry, computed with the Gromov-Wasserstein distance, into Transformer cross-attention and improves low-overlap point cloud registration.
Spinnet: Learning a general surface descrip- tor for 3d point cloud registration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Fully-Geometric Cross-Attention for Point Cloud Registration
FLAT embeds rotation- and translation-invariant cross-cloud geometry, computed with the Gromov-Wasserstein distance, into Transformer cross-attention and improves low-overlap point cloud registration.