The author proposes PCR-99 as a robust method for point cloud registration, handling extreme outlier ratios up to 99% efficiently.
EYOC proposes an unsupervised method for distant point cloud registration, adapting to new data distributions without global pose labels.
Novel framework for robust cross-source point cloud registration using spherical voxels and hierarchical correspondence filtering.
SPEALは、骨格埋め込み注意学習を使用して、異なるソースのポイントクラウド登録を効果的に行います。
ReLaTo introduces a novel approach for large transformation point cloud registration, outperforming existing methods.
SPEAL는 해부학적 선입견을 활용하여 점군의 지오메트리 복잡성을 캡처하고 등록을 용이하게 합니다.
Effektive Nutzung von Skelettgeometrie für präzise Punktewolkenregistrierung.
Our approach directly matches superpoints between input point clouds to robustly estimate the SE(3) transformation matrix, without relying on cumbersome post-processing steps.
A robust point cloud registration approach that leverages graph neural partial differential equations and heat kernel signatures to enhance the robustness of feature representations and efficiently obtain corresponding keypoints.
This paper introduces LoGDesc, a novel hybrid descriptor that leverages local geometric features and learning-based feature propagation to achieve robust 3D point cloud registration, particularly in challenging scenarios with noise and low overlap.