Geodesic eccentricity helps detect 3D keypoints on objects
GEKey: Learning Geodesic Eccentric 3D Keypoints via Self-Supervision
Computer Vision and Pattern Recognition
Summary
Detecting important points on 3D objects helps computers understand shapes. The authors created GEKey, a method that finds special points on objects without needing human labels. It uses a geometric property called geodesic eccentricity to find points that stand out for each object. Their method works well even when objects are noisy, incomplete, or change shape.
What this means in practice
- •For 3d computer vision developers: Train models to find important points on 3D scans without human labeling, improving shape understanding and alignment in real-world scenarios.
- •For robotic perception engineers: Use GEKey to robustly identify keypoints on objects for tasks like manipulation or navigation despite noise and shape changes.
Authors
Pierre Onghena, Santiago Velasco-Forero, Beatriz Marcotegui
Abstract
Point clouds represent 3D object geometry as sets of spatial coordinates. A fundamental task in their analysis is keypoint detection, i.e., identifying a sparse subset of points that captures the most salient features. While supervised methods rely on manual annotations, unsupervised approaches leverage intrinsic geometric properties to localize keypoints without human input. We introduce GEKey, a self-supervised framework that uses the geodesic eccentricity transform, an SE(3)-invariant geometric measure, to identify instance-specific salient points. These points serve as pseudo-labels to train a model that aligns its predictions with the object's intrinsic structure. GEKey is simple, efficient, and robust, preserving intra-class variation by balancing instance-specific and category-level structure. Extensive experiments on ShapeNetCoreV2, KeypointNet, CAPE, ITOP, and DeformingThings4D show state-of-the-art performance in both keypoint detection and alignment, with strong resilience to noise, downsampling, deformations, and real-world conditions. The code and pretrained models are available at https://github.com/Pierreoo/GEKey.