Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions

TL;DR

This paper introduces benchmark datasets for evaluating 6DOF outdoor visual localization under varying conditions, highlighting current challenges and suggesting future research directions.

Contribution

It provides the first specialized benchmarks for analyzing the impact of environmental factors on visual localization accuracy.

Findings

Long-term localization remains challenging under changing conditions.

Sequence-based localization approaches show promise.

Better local features are needed for improved accuracy.

Abstract

Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing condition, including day-night changes, as well as weather and seasonal variations, while providing highly accurate 6 degree-of-freedom (6DOF) camera pose estimates. In this paper, we introduce the first benchmark datasets specifically designed for analyzing the impact of such factors on visual localization. Using carefully created ground truth poses for query images taken under a wide variety of conditions, we evaluate the impact of various factors on 6DOF camera pose estimation accuracy through extensive experiments with state-of-the-art localization approaches. Based on our results, we draw conclusions about the difficulty of different conditions, showing that long-term localization is far from solved, and propose promising avenues for future work, including sequence-based localization approaches and the need for better local features. Our benchmark is available at visuallocalization.net.