PoseINN: Realtime Visual-based Pose Regression and Localization with Invertible Neural Networks

Zirui Zang, Ahmad Amine, Rahul Mangharam

Keywords: pose regression, localization, normalizing flows, invertible neural network

TL;DR: Proposing visual pose regression and localization with normalizing flows using NeRF as image simulators.

Abstract:

Estimating ego-pose from cameras is an important
problem in robotics with applications ranging from mobile
robotics to augmented reality. While SOTA models are becoming
increasingly accurate, they can still be unwieldy due to high
computational costs. In this paper, we propose to solve the
problem by using invertible neural networks (INN) to find the
mapping between the latent space of images and poses for a
given scene. Our model achieves similar performance to the
SOTA while being faster to train and only requiring offline
rendering of low-resolution synthetic data. By using normalizing
flows, the proposed method also provides uncertainty estimation
for the output. We also demonstrated the efficiency of this
method by deploying the model on a mobile robot.

Submission Number: 17