DarkSLAM: GAN-assisted Visual SLAM for Reliable Operation in Low-light Conditions

TL;DR

DarkSLAM introduces a GAN-assisted preprocessing step to enhance low-light images, significantly improving visual SLAM robustness and tracking reliability in dark environments compared to existing methods.

Contribution

The paper presents a novel GAN-based preprocessing module that enables visual SLAM to operate reliably in low-light conditions, a challenge not adequately addressed by prior approaches.

Findings

Achieves 25.1% tracking time in darkest sequences, outperforming existing methods at 0.6%.

Maintains high localization reliability even in extremely low light.

Validated on a custom indoor dataset with varying illumination levels.

Abstract

Existing visual SLAM approaches are sensitive to illumination, with their precision drastically falling in dark conditions due to feature extractor limitations. The algorithms currently used to overcome this issue are not able to provide reliable results due to poor performance and noisiness, and the localization quality in dark conditions is still insufficient for practical use. In this paper, we present a novel SLAM method capable of working in low light using Generative Adversarial Network (GAN) preprocessing module to enhance the light conditions on input images, thus improving the localization robustness. The proposed algorithm was evaluated on a custom indoor dataset consisting of 14 sequences with varying illumination levels and ground truth data collected using a motion capture system. According to the experimental results, the reliability of the proposed approach remains high even in extremely low light conditions, providing 25.1% tracking time on darkest sequences, whereas existing approaches achieve tracking only 0.6% of the sequence time.