PoseINN: 可逆ニューラルネットワークによるリアルタイム視覚ベースの姿勢回帰と自己位置推定
PoseINN: Realtime Visual-based Pose Regression and Localization with Invertible Neural Networks
可逆ニューラルネットワーク(INN)を用いて画像の潜在空間と姿勢の対応を学習し、低解像度の合成データのみで高速に学習できるリアルタイム視覚自己位置推定手法を提案。不確かさ推定も可能で、移動ロボットへの実装も実証した。
著者: Zirui Zang, Ahmad Amine, Rahul Mangharam
分類: cs.RO, cs.CV
原文アブストラクト
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.
