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.
Point cloud registration: a mini-review of current state, challenging is- sues and future directions.AIMS Geosciences, 9(1):68–85,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.