Improving Nighttime Retrieval-based Localization

Abstract

Outdoor visual localization is a crucial component to many computer vision systems. We propose an approach to localization from images that is designed to explicitly handle the strong variations in appearance happening between daytime and nighttime. As revealed by recent long-term localization benchmarks, both traditional feature-based and retrieval-based approaches still struggle to handle such changes. Our novel localization method combines a state-of-the-art image retrieval architecture with condition-specific sub-networks allowing the computation of global image descriptors that are explicitly dependent of the capturing conditions. We show that our approach improves localization by a factor of almost 300% compared to the popular VLAD-based methods on nighttime localization.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygermain2018improving

Related papers

• Night-to-day Image Translation For Retrieval-based Localization (2018)16.88
• Benchmarking Image Retrieval For Visual Localization (2020)17.78
• Adversarial Training For Adverse Conditions: Robust Metric Localisation Using Appearance Transfer (2018)14.43
• Investigating The Role Of Image Retrieval For Visual Localization -- An Exhaustive Benchmark (2022)16.58
• Learning Condition Invariant Features For Retrieval-based Localization From 1M Images (2020)0.00
• Improved Visual Localization Via Graph Smoothing (2019)0.00
• Training Semantic Descriptors For Image-based Localization (2022)0.00
• Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11