A new large real-world cross-source LiDAR registration benchmark and a visual-geometric attention method that lowers rotation error by 63% and translation error by 40% compared to GeoTrans on it.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark
A new large real-world cross-source LiDAR registration benchmark and a visual-geometric attention method that lowers rotation error by 63% and translation error by 40% compared to GeoTrans on it.