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