# Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning

arXiv: https://arxiv.org/abs/1903.10543 · HTML: https://mlsanity.com/paper/1903.10543/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2019.

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

- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks](https://mlsanity.com/paper/2104.07196/) (2021)
- [DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry](https://mlsanity.com/paper/2105.09899/) (2021)
- [AFT-VO: Asynchronous Fusion Transformers for Multi-View Visual Odometry Estimation](https://mlsanity.com/paper/2206.12946/) (2022)
- [A Consistency-Based Loss for Deep Odometry Through Uncertainty Propagation](https://mlsanity.com/paper/2107.00366/) (2021)
- [RAM-VO: Less is more in Visual Odometry](https://mlsanity.com/paper/2107.02974/) (2021)
- [ATDN vSLAM: An all-through Deep Learning-Based Solution for Visual Simultaneous Localization and Mapping](https://mlsanity.com/paper/2206.05963/) (2022)
- [Robust Monocular Visual Odometry using Curriculum Learning](https://mlsanity.com/paper/2411.13438/) (2024)

## Abstract (arXiv)

Inspired by the cognitive process of humans and animals, Curriculum Learning (CL) trains a model by gradually increasing the difficulty of the training data. In this paper, we study whether CL can be applied to complex geometry problems like estimating monocular Visual Odometry (VO). Unlike existing CL approaches, we present a novel CL strategy for learning the geometry of monocular VO by gradually making the learning objective more difficult during training. To this end, we propose a novel geometry-aware objective function by jointly optimizing relative and composite transformations over small windows via bounded pose regression loss. A cascade optical flow network followed by recurrent network with a differentiable windowed composition layer, termed CL-VO, is devised to learn the proposed objective. Evaluation on three real-world datasets shows superior performance of CL-VO over state-of-the-art feature-based and learning-based VO.