DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching

arXiv:2306.12547v2 Announce Type: replace
Abstract: Matching 2D keypoints in an image to a sparse 3D point cloud of the scene without requiring visual descriptors has garnered increased interest due to its low memory requirements, inherent privacy preservation, and reduced need for expensive 3D model maintenance compared to visual descriptor-based methods. However, existing algorithms often compromise on performance, resulting in a significant deterioration compared to their descriptor-based counterparts. In this paper, we introduce DGC-GNN, a novel algorithm that employs a global-to-local …

abstract arxiv cloud color cs.cv free geometry gnn image low maintenance memory preservation privacy requirements type visual