DeLightMono: Enhancing Self-Supervised Monocular Depth Estimation in Endoscopy by Decoupling Uneven Illumination

TL;DR

DeLightMono introduces a self-supervised framework for monocular depth estimation in endoscopy that decouples illumination, reflectance, and depth to improve accuracy under uneven lighting conditions.

Contribution

It proposes a novel illumination-reflectance-depth model and a joint-optimization framework specifically designed for endoscopic images with uneven illumination.

Findings

Significantly improves depth estimation accuracy in uneven lighting conditions.

Outperforms existing methods on public endoscopic datasets.

Ablation studies confirm the effectiveness of illumination decoupling.

Abstract

Self-supervised monocular depth estimation serves as a key task in the development of endoscopic navigation systems. However, performance degradation persists due to uneven illumination inherent in endoscopic images, particularly in low-intensity regions. Existing low-light enhancement techniques fail to effectively guide the depth network. Furthermore, solutions from other fields, like autonomous driving, require well-lit images, making them unsuitable and increasing data collection burdens. To this end, we present DeLight-Mono - a novel self-supervised monocular depth estimation framework with illumination decoupling. Specifically, endoscopic images are represented by a designed illumination-reflectance-depth model, and are decomposed with auxiliary networks. Moreover, a self-supervised joint-optimizing framework with novel losses leveraging the decoupled components is proposed to mitigate the effects of uneven illumination on depth estimation. The effectiveness of the proposed methods was rigorously verified through extensive comparisons and an ablation study performed on two public datasets.