GeGS-PCR combines a color encoder, Geometric-3DGS module, LORA optimization, and joint photometric loss to achieve 99.9% registration recall and sub-0.03 rotation/translation errors on colorized 3DMatch and Kitti benchmarks.
Unsupervised point cloud registration by learning unified gaussian mixture models.IEEE Robotics and Automation Letters, 7(3):7028–7035
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion
GeGS-PCR combines a color encoder, Geometric-3DGS module, LORA optimization, and joint photometric loss to achieve 99.9% registration recall and sub-0.03 rotation/translation errors on colorized 3DMatch and Kitti benchmarks.