LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation
This work addresses robust visual odometry for robotics or autonomous systems, but it is incremental as it builds on prior linear approximations with a non-linear extension.
The paper tackles the camera ego-motion estimation problem by proposing LS-VO, a deep network that learns a non-linear latent space for optical flow features, resulting in a considerable performance increase over baselines with only a slight parameter increase.
This work proposes a novel deep network architecture to solve the camera Ego-Motion estimation problem. A motion estimation network generally learns features similar to Optical Flow (OF) fields starting from sequences of images. This OF can be described by a lower dimensional latent space. Previous research has shown how to find linear approximations of this space. We propose to use an Auto-Encoder network to find a non-linear representation of the OF manifold. In addition, we propose to learn the latent space jointly with the estimation task, so that the learned OF features become a more robust description of the OF input. We call this novel architecture LS-VO. The experiments show that LS-VO achieves a considerable increase in performances in respect to baselines, while the number of parameters of the estimation network only slightly increases.