i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

TL;DR

i3dLoc introduces a robust cross-domain localization method that effectively matches images to 3D maps despite environmental variations, using condition-invariant features and spherical convolution networks to improve accuracy and generalization.

Contribution

The paper proposes a novel approach combining GAN-based feature disentanglement and spherical convolution to achieve environment-invariant localization across diverse conditions and large-scale environments.

Findings

Achieves 3x higher place retrievals in inconsistent environments.

Over 3x improvement in online localization accuracy.

Demonstrates strong generalization across different datasets.

Abstract

We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between image and 3D. The problem is even more challenging as the method must handle various environmental conditions such as illumination, weather, and seasonal changes. Our method can match equirectangular images to the 3D range projections by extracting cross-domain symmetric place descriptors. Our key insight is to retain condition-invariant 3D geometry features from limited data samples while eliminating the condition-related features by a designed Generative Adversarial Network. Based on such features, we further design a spherical convolution network to learn viewpoint-invariant symmetric place descriptors. We evaluate our method on extensive self-collected datasets, which involve \textit{Long-term} (variant appearance conditions), \textit{Large-scale} (up to $2km$ structure/unstructured environment), and \textit{Multistory} (four-floor confined space). Our method surpasses other current state-of-the-arts by achieving around $3$ times higher place retrievals to inconsistent environments, and above $3$ times accuracy on online localization. To highlight our method's generalization capabilities, we also evaluate the recognition across different datasets. With a single trained model, i3dLoc can demonstrate reliable visual localization in random conditions.