Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes
This addresses the mismatch between static indoor benchmarks and real-world dynamic indoor environments for computer vision and robotics applications, but it is incremental as it adapts an existing dataset.
The authors tackled the problem of long-term camera re-localization in changing indoor scenes by creating the RIO10 benchmark from the 3RScan dataset, proposing new evaluation metrics, and showing that state-of-the-art methods perform poorly, indicating it remains an unsolved problem.
Long-term camera re-localization is an important task with numerous computer vision and robotics applications. Whilst various outdoor benchmarks exist that target lighting, weather and seasonal changes, far less attention has been paid to appearance changes that occur indoors. This has led to a mismatch between popular indoor benchmarks, which focus on static scenes, and indoor environments that are of interest for many real-world applications. In this paper, we adapt 3RScan - a recently introduced indoor RGB-D dataset designed for object instance re-localization - to create RIO10, a new long-term camera re-localization benchmark focused on indoor scenes. We propose new metrics for evaluating camera re-localization and explore how state-of-the-art camera re-localizers perform according to these metrics. We also examine in detail how different types of scene change affect the performance of different methods, based on novel ways of detecting such changes in a given RGB-D frame. Our results clearly show that long-term indoor re-localization is an unsolved problem. Our benchmark and tools are publicly available at waldjohannau.github.io/RIO10