HCPM: Hierarchical Candidates Pruning for Efficient Detector-Free Matching

arXiv:2403.12543v1 Announce Type: new
Abstract: Deep learning-based image matching methods play a crucial role in computer vision, yet they often suffer from substantial computational demands. To tackle this challenge, we present HCPM, an efficient and detector-free local feature-matching method that employs hierarchical pruning to optimize the matching pipeline. In contrast to recent detector-free methods that depend on an exhaustive set of coarse-level candidates for matching, HCPM selectively concentrates on a concise subset of informative candidates, resulting in fewer computational candidates …

abstract arxiv challenge computational computer computer vision contrast cs.cv deep learning feature free hierarchical image pipeline pruning role type vision