Learning to Predict Repeatability of Interest Points
This work addresses the problem of robust interest point selection for robotics applications like visual localization, offering an incremental improvement by predicting repeatability to enhance map summarization.
The paper tackles the challenge of predicting the repeatability of interest points over time under varying environmental conditions, proposing a repeatability predictor (RP) that estimates when a new interest point will be repeated and significantly mitigates localization accuracy degeneration in map summarization.
Many robotics applications require interest points that are highly repeatable under varying viewpoints and lighting conditions. However, this requirement is very challenging as the environment changes continuously and indefinitely, leading to appearance changes of interest points with respect to time. This paper proposes to predict the repeatability of an interest point as a function of time, which can tell us the lifespan of the interest point considering daily or seasonal variation. The repeatability predictor (RP) is formulated as a regressor trained on repeated interest points from multiple viewpoints over a long period of time. Through comprehensive experiments, we demonstrate that our RP can estimate when a new interest point is repeated, and also highlight an insightful analysis about this problem. For further comparison, we apply our RP to the map summarization under visual localization framework, which builds a compact representation of the full context map given the query time. The experimental result shows a careful selection of potentially repeatable interest points predicted by our RP can significantly mitigate the degeneration of localization accuracy from map summarization.