A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera Relocalization

TL;DR

This paper introduces A2-GNN, a novel graph neural network that enhances descriptor-free camera relocalization by efficiently capturing local geometric structures, achieving state-of-the-art accuracy with low computational cost.

Contribution

The paper proposes a simple yet effective A2-GNN model that improves geometric structural learning for descriptor-free camera localization, addressing accuracy and efficiency limitations of prior methods.

Findings

Achieves state-of-the-art accuracy among descriptor-free methods.

Operates with low computational overhead.

Effectively captures local geometric structures.

Abstract

Visual localization involves estimating the 6-degree-of-freedom (6-DoF) camera pose within a known scene. A critical step in this process is identifying pixel-to-point correspondences between 2D query images and 3D models. Most advanced approaches currently rely on extensive visual descriptors to establish these correspondences, facing challenges in storage, privacy issues and model maintenance. Direct 2D-3D keypoint matching without visual descriptors is becoming popular as it can overcome those challenges. However, existing descriptor-free methods suffer from low accuracy or heavy computation. Addressing this gap, this paper introduces the Angle-Annular Graph Neural Network (A2-GNN), a simple approach that efficiently learns robust geometric structural representations with annular feature extraction. Specifically, this approach clusters neighbors and embeds each group's distance information and angle as supplementary information to capture local structures. Evaluation on matching and visual localization datasets demonstrates that our approach achieves state-of-the-art accuracy with low computational overhead among visual description-free methods. Our code will be released on https://github.com/YejunZhang/a2-gnn.