LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation

09/18/2017
by   Gabriele Costante, et al.
0

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.

READ FULL TEXT

page 1

page 4

page 5

research
07/28/2020

Robust Ego and Object 6-DoF Motion Estimation and Tracking

The problem of tracking self-motion as well as motion of objects in the ...
research
07/16/2019

Scene Motion Decomposition for Learnable Visual Odometry

Optical Flow (OF) and depth are commonly used for visual odometry since ...
research
11/22/2021

Robust Visual Odometry Using Position-Aware Flow and Geometric Bundle Adjustment

In this paper, an essential problem of robust visual odometry (VO) is ap...
research
05/29/2017

Towards Visual Ego-motion Learning in Robots

Many model-based Visual Odometry (VO) algorithms have been proposed in t...
research
03/15/2022

MotionCLIP: Exposing Human Motion Generation to CLIP Space

We introduce MotionCLIP, a 3D human motion auto-encoder featuring a late...
research
07/05/2023

Wasserstein Auto-Encoders of Merge Trees (and Persistence Diagrams)

This paper presents a computational framework for the Wasserstein auto-e...
research
02/08/2021

Analysis of Latent-Space Motion for Collaborative Intelligence

When the input to a deep neural network (DNN) is a video signal, a seque...

Please sign up or login with your details

Forgot password? Click here to reset