Information-Theoretic Odometry Learning

TL;DR

This paper introduces an information-theoretic framework for odometry estimation that uses a variational information bottleneck to improve accuracy, interpretability, and uncertainty quantification in real-time robotics and vision applications.

Contribution

It formulates odometry learning as an information bottleneck problem, providing theoretical bounds and practical tools for model design and uncertainty estimation.

Findings

Effective odometry estimation demonstrated on two datasets.

The framework bounds generalization errors and enhances interpretability.

Uncertainty quantification achieved without extra computational overhead.

Abstract

In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative camera poses are required in real time. We formulate this problem as optimizing a variational information bottleneck objective function, which eliminates pose-irrelevant information from the latent representation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language. Specifically, we bound the generalization errors of the deep information bottleneck framework and the predictability of the latent representation. These provide not only a performance guarantee but also practical guidance for model design, sample collection, and sensor selection. Furthermore, the stochastic latent representation provides a natural uncertainty measure without the needs for extra structures or computations. Experiments on two well-known odometry datasets demonstrate the effectiveness of our method.