Generalized Correspondence Matching via Flexible Hierarchical Refinement and Patch Descriptor Distillation

arXiv:2403.05388v1 Announce Type: new
Abstract: Correspondence matching plays a crucial role in numerous robotics applications. In comparison to conventional hand-crafted methods and recent data-driven approaches, there is significant interest in plug-and-play algorithms that make full use of pre-trained backbone networks for multi-scale feature extraction and leverage hierarchical refinement strategies to generate matched correspondences. The primary focus of this paper is to address the limitations of deep feature matching (DFM), a state-of-the-art (SoTA) plug-and-play correspondence matching approach. First, we eliminate the …

abstract algorithms applications arxiv comparison cs.cv data data-driven distillation extraction feature feature extraction generalized hierarchical networks robotics role scale strategies type via