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.

翻译：从摄像头估计自我位姿是机器人领域中的一个重要问题，其应用涵盖移动机器人到增强现实等范围。尽管当前最先进的模型在精度上不断提升，但由于计算成本高昂，仍显得笨重。本文提出利用可逆神经网络（INN）解决该问题，以寻找给定场景中图像潜在空间与位姿之间的映射。所提模型在达到与最先进方法相近性能的同时，训练速度更快，且仅需离线渲染低分辨率合成数据。通过使用归一化流，该方法还能为输出提供不确定性估计。我们还将该模型部署至移动机器人，验证了其效率。