Point Cloud Registration

Point Cloud Registration is a fundamental problem in 3D computer vision and photogrammetry. Given several sets of points in different coordinate systems, the aim of registration is to find the transformation that best aligns all of them into a common coordinate system. Point Cloud Registration plays a significant role in many vision applications such as 3D model reconstruction, cultural heritage management, landslide monitoring and solar energy analysis.

Source: Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registration

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 447 papers

Title	Date	Tasks	Status	Hype
A Multi-Level Similarity Approach for Single-View Object Grasping: Matching, Planning, and Fine-Tuning	Jul 16, 2025	ObjectPoint Cloud Registration	—Unverified	0
Simultaneous Localization and Mapping Using Active mmWave Sensing in 5G NR	Jul 7, 2025	Loop Closure DetectionPoint Cloud Generation	—Unverified	0
CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection	Jun 26, 2025	global-optimizationImage to Point Cloud Registration	—Unverified	0
Correspondence-Free Multiview Point Cloud Registration via Depth-Guided Joint Optimisation	Jun 18, 2025	Point Cloud Registration	—Unverified	0
MT-PCR: A Hybrid Mamba-Transformer with Spatial Serialization for Hierarchical Point Cloud Registration	Jun 16, 2025	GPUMamba	—Unverified	0
Robust Filtering -- Novel Statistical Learning and Inference Algorithms with Applications	Jun 13, 2025	Autonomous VehiclesBayesian Inference	—Unverified	0
Rectified Point Flow: Generic Point Cloud Pose Estimation	Jun 5, 2025	Point Cloud RegistrationPose Estimation	—Unverified	0
Cross-modal feature fusion for robust point cloud registration with ambiguous geometry	May 19, 2025	Point Cloud Registration	CodeCode Available	1
MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos	May 17, 2025	Depth EstimationOptical Flow Estimation	—Unverified	0
FA-KPConv: Introducing Euclidean Symmetries to KPConv via Frame Averaging	May 7, 2025	Point Cloud ClassificationPoint Cloud Registration	—Unverified	0

Show:10 25 50

← PrevPage 1 of 45Next →

All datasets ETH (trained on 3DMatch)3DMatch Benchmark 3DMatch (at least 30% overlapped - FCGF setting)KITTI (trained on 3DMatch)3DLoMatch (10-30% overlap)3DMatch (at least 30% overlapped - sample 5k interest points)KITTI (FCGF setting)FPv1 FP-O-E FP-O-H FP-O-M FP-R-E

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	CoFF	Recall ( correspondence RMSE below 0.2)	81.6	—	Unverified
2	GeoTransformer - P2PNet	Recall ( correspondence RMSE below 0.2)	74	—	Unverified
3	NgeNet	Recall ( correspondence RMSE below 0.2)	71.9	—	Unverified
4	REGTR	Recall ( correspondence RMSE below 0.2)	64.8	—	Unverified
5	Predator-1k	Recall ( correspondence RMSE below 0.2)	62.5	—	Unverified
6	Predator-5k	Recall ( correspondence RMSE below 0.2)	59.8	—	Unverified
7	PCAM (reported in REGTR)	Recall ( correspondence RMSE below 0.2)	54.9	—	Unverified
8	DGR (reported in REGTR)	Recall ( correspondence RMSE below 0.2)	48.7	—	Unverified
9	FCGF (reported in PREDATOR)	Recall ( correspondence RMSE below 0.2)	40.1	—	Unverified
10	D3Feat (reported in PREDATOR)	Recall ( correspondence RMSE below 0.2)	37.2	—	Unverified