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

arXiv: https://arxiv.org/abs/1709.06019 · HTML: https://mlsanity.com/paper/1709.06019/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2017.

## Built on by (most cited first, 7 of 7)

- [Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applications](https://mlsanity.com/paper/2107.11750/) (2021)
- [Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry](https://mlsanity.com/paper/2401.05396/) (2023)
- [Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments](https://mlsanity.com/paper/2304.07250/) (2023)
- [GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method](https://mlsanity.com/paper/2112.04054/) (2021)
- [Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines](https://mlsanity.com/paper/2503.02955/) (2025)
- [Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression](https://mlsanity.com/paper/2208.00919/) (2022)
- [Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation](https://mlsanity.com/paper/2208.08892/) (2022)

## Abstract (arXiv)

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.