# Learning monocular visual odometry with dense 3D mapping from dense 3D flow

arXiv: https://arxiv.org/abs/1803.02286 · HTML: https://mlsanity.com/paper/1803.02286/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2018.

## Built on by (most cited first, 8 of 8)

- [Bimodal Camera Pose Prediction for Endoscopy](https://mlsanity.com/paper/2204.04968/) (2022)
- [VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals](https://mlsanity.com/paper/2104.06789/) (2021)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [MDN-VO: Estimating Visual Odometry with Confidence](https://mlsanity.com/paper/2112.12812/) (2021)
- [RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry](https://mlsanity.com/paper/2203.07162/) (2022)
- [Visual Heading Prediction for Autonomous Aerial Vehicles](https://mlsanity.com/paper/2512.09898/) (2025)
- [A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation](https://mlsanity.com/paper/2203.04812/) (2022)
- [RAM-VO: Less is more in Visual Odometry](https://mlsanity.com/paper/2107.02974/) (2021)

## Abstract (arXiv)

This paper introduces a fully deep learning approach to monocular SLAM, which can perform simultaneous localization using a neural network for learning visual odometry (L-VO) and dense 3D mapping. Dense 2D flow and a depth image are generated from monocular images by sub-networks, which are then used by a 3D flow associated layer in the L-VO network to generate dense 3D flow. Given this 3D flow, the dual-stream L-VO network can then predict the 6DOF relative pose and furthermore reconstruct the vehicle trajectory. In order to learn the correlation between motion directions, the Bivariate Gaussian modelling is employed in the loss function. The L-VO network achieves an overall performance of 2.68% for average translational error and 0.0143 deg/m for average rotational error on the KITTI odometry benchmark. Moreover, the learned depth is fully leveraged to generate a dense 3D map. As a result, an entire visual SLAM system, that is, learning monocular odometry combined with dense 3D mapping, is achieved.