# Learning-based Image Enhancement for Visual Odometry in Challenging HDR Environments

arXiv: https://arxiv.org/abs/1707.01274 · HTML: https://mlsanity.com/paper/1707.01274/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2017.

## Built on by (most cited first, 5 of 5)

- [Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching](https://mlsanity.com/paper/2102.04341/) (2021)
- [Fast and Accurate: Video Enhancement using Sparse Depth](https://mlsanity.com/paper/2103.08764/) (2021)
- [Active Illumination Control in Low-Light Environments using NightHawk](https://mlsanity.com/paper/2506.06394/) (2025)
- [Reproducible Evaluation of Camera Auto-Exposure Methods in the Field: Platform, Benchmark and Lessons Learned](https://mlsanity.com/paper/2506.18844/) (2025)
- [Adaptive Illumination Control for Robot Perception](https://mlsanity.com/paper/2602.15900/) (2026)

## Abstract (arXiv)

One of the main open challenges in visual odometry (VO) is the robustness to difficult illumination conditions or high dynamic range (HDR) environments. The main difficulties in these situations come from both the limitations of the sensors and the inability to perform a successful tracking of interest points because of the bold assumptions in VO, such as brightness constancy. We address this problem from a deep learning perspective, for which we first fine-tune a Deep Neural Network (DNN) with the purpose of obtaining enhanced representations of the sequences for VO. Then, we demonstrate how the insertion of Long Short Term Memory (LSTM) allows us to obtain temporally consistent sequences, as the estimation depends on previous states. However, the use of very deep networks does not allow the insertion into a real-time VO framework; therefore, we also propose a Convolutional Neural Network (CNN) of reduced size capable of performing faster. Finally, we validate the enhanced representations by evaluating the sequences produced by the two architectures in several state-of-art VO algorithms, such as ORB-SLAM and DSO.