Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation

Depth estimation from monocular images is an important task in localization and 3D reconstruction pipelines for bronchoscopic navigation. Various supervised self-supervised deep learning-based approaches have proven themselves on this natural images. However, the lack of labeled data bronchial tissue’s feature-scarce texture make utilization these methods ineffective scenes. In work, we propose alternative domain-adaptive approach. Our novel two-step structure first trains a depth network with synthetic manner; then adopts unsupervised adversarial domain feature adaptation scheme to improve performance real The results our experiments show that proposed method improves network’s by considerable margin can be employed pipelines.