[ECCV 2024] UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration
-
Updated
Aug 24, 2024 - Python
[ECCV 2024] UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration
register 3D point clouds using rotation, translation, and scale transformations.
Comparison of SHOT and FPFH descriptors for 3D point clouds registration
Bayesian Coherent Point Drift (BCPD/BCPD++/GBCPD/GBCPD++)
[IEEE TGRS 2024] A novel method for registration of MLS and stereo reconstructed point clouds
This repository contains the code developed for my MSc project titled "Exploring Photogrammetry for High-Fidelity 3D Model Generation: A Power Grid Inspection Study", as well as some of the results. The thesis was written in collaboration with SINTEF, and the degree issued by DTU. The full thesis can be downloaded from the below link.
FLS point cloud registration library.
[CVPR 2023] Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
Fast and robust global registration for terrestrial robots @ ICRA2022
K-Closest Points and Maximum Clique Pruning for Efficient and Effective 3-D Laser Scan Matching (RA-L 2022)
[IEEE TMM 2024] IGReg: Image-Geometry-Assisted Point Cloud Registration via Selective Correlation Fusion
Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)
image registration related books, papers, videos, and toolboxes
Implementation of Iterative Closest Point and Trimmed Iterative Closest Point algorithms.
PyTorch implementation of DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration (BMVC 2021)
We refined the quantile assignment algorithm by integrating prevalent feature descriptors and transformation estimation methods to enhance the correspondence between the source and target point clouds.
[ICME 2024] VRHCF: Cross-Source Point Cloud Registration via Voxel Representation and Hierarchical Correspondence Filtering
[ICME 2023, Oral]HybridPoint: Point cloud registration based on hybrid point sampling and matching
Frame-to-Frame Registration using Gaussian Mixture Models.
Add a description, image, and links to the point-cloud-registration topic page so that developers can more easily learn about it.
To associate your repository with the point-cloud-registration topic, visit your repo's landing page and select "manage topics."