SOURCE-LINKED INTELLIGENCE

Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Learning-based image-to-point-cloud (I2P) registration has garnered increasing attention in recent years. Nevertheless, existing methods still struggle with severe outliers under challenging scenarios with unseen, low-inlier, or distorted cases. A fast and robust 2D-3D correspondence pruning method is therefore highly desirable. Recently, a promising scheme lifts 2D-3D correspondences to 3D-3D correspondences using depth priors, casting correspondence pruning as a Sim(3) registration problem. However, depth priors estimated from monocular images are inherently noisy, which undermines the relia

Read original source ↗ Open in workspace

recordType

paper

region

Global