Learning models for visual 3D localization with implicit mapping

Dan Rosenbaum, Frederic Besse, Fabio Viola, Danilo J. Rezende, S. M. Ali Eslami

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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, for instance that of objects. 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.
Original languageEnglish
Title of host publicationBayesian Deep Learning workshop, Neural Information Processing Systems(NeurIPS)
StatePublished - 2018
Externally publishedYes

Fingerprint

Dive into the research topics of 'Learning models for visual 3D localization with implicit mapping'. Together they form a unique fingerprint.

Cite this