Search Results for author:
Found 6 papers, 5 papers with code
REGTR: End-to-end Point Cloud Correspondences with Transformers
Despite recent success in incorporating learning into point cloud registration, many works focus on learning feature descriptors and continue to rely on nearest-neighbor feature matching and outlier filtering through RANSAC to obtain the final set of correspondences for pose estimation.
Learning Iterative Robust Transformation Synchronization
Transformation Synchronization is the problem of recovering absolute transformations from a given set of pairwise relative motions.
City-scale Scene Change Detection using Point Clouds
We propose a method for detecting structural changes in a city using images captured from vehicular mounted cameras over traversals at two different times.
RPM-Net: Robust Point Matching using Learned Features
The hard assignments of closest point correspondences based on spatial distances are sensitive to the initial rigid transformation and noisy/outlier points, which often cause ICP to converge to wrong local minima.
Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes
Furthermore, we show that by using a Gaussian-Uniform mixture model, our approach degenerates to the formulation of a state-of-the-art approach for robust indoor reconstruction.
3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision.
Ranked #6 on
Point Cloud Registration
on KITTI
