Learning models for visual 3D localization with implicit mapping
This addresses visual localization for robotics or AR/VR, but it is incremental as it builds on existing GQN methods with a novel attention mechanism.
The paper tackles the problem of visual 3D localization by learning implicit representations without explicit maps, using an enhanced Generative Query Network on procedurally generated Minecraft scenes, and shows it can capture scene structure and be applied to localization with comparisons to a discriminative baseline.
We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an implicit representation of the environment at a higher, more abstract level. We propose to use a generative approach based on Generative Query Networks (GQNs, Eslami et al. 2018), asking the following questions: 1) Can GQN capture more complex scenes than those it was originally demonstrated on? 2) Can GQN be used for localization in those scenes? To study this approach we consider procedurally generated Minecraft worlds, for which we can generate images of complex 3D scenes along with camera pose coordinates. We first show that GQNs, enhanced with a novel attention mechanism can capture the structure of 3D scenes in Minecraft, as evidenced by their samples. We then apply the models to the localization problem, comparing the results to a discriminative baseline, and comparing the ways each approach captures the task uncertainty.