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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Shuzhe, Kannala, Juho, Barath, Daniel
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929286819086336
author Wang, Shuzhe
Kannala, Juho
Barath, Daniel
author_facet Wang, Shuzhe
Kannala, Juho
Barath, Daniel
contents 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 Graph Neural Network (GNN) that progressively exploits geometric and color cues to represent keypoints, thereby improving matching accuracy. Our procedure encodes both Euclidean and angular relations at a coarse level, forming the geometric embedding to guide the point matching. We evaluate DGC-GNN on both indoor and outdoor datasets, demonstrating that it not only doubles the accuracy of the state-of-the-art visual descriptor-free algorithm but also substantially narrows the performance gap between descriptor-based and descriptor-free methods.
format Preprint
id arxiv_https___arxiv_org_abs_2306_12547
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching
Wang, Shuzhe
Kannala, Juho
Barath, Daniel
Computer Vision and Pattern Recognition
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 Graph Neural Network (GNN) that progressively exploits geometric and color cues to represent keypoints, thereby improving matching accuracy. Our procedure encodes both Euclidean and angular relations at a coarse level, forming the geometric embedding to guide the point matching. We evaluate DGC-GNN on both indoor and outdoor datasets, demonstrating that it not only doubles the accuracy of the state-of-the-art visual descriptor-free algorithm but also substantially narrows the performance gap between descriptor-based and descriptor-free methods.
title DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.12547