Images of a given environment, coded by a holistic image descriptor, produce a manifold that is articulated by the camera pose in such environment. The correct articulation of such Descriptor Manifold (DM) by the camera poses is the cornerstone for precise Appearance-based Localization (AbL), which implies knowing the correspondent descriptor for any given pose of the camera in the environment. Since such correspondences are only given at sample pairs of the DM (the appearance map), some kind of regression must be applied to predict descriptor values at unmapped locations. This is relevant for AbL because this regression process can be exploited as an observation model for the localization task. This paper analyses the influence of a number of parameters involved in the approximation of the DM from the appearance map, including the sampling density, the method employed to regress values at unvisited poses, and the impact of the image content on the DM structure. We present experimental evaluations of diverse setups and propose an image metric based on the image derivatives, which allows us to build appearance maps in the form of grids of variable density. A preliminary use case is presented as an initial step for future research.
