Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation

TL;DR

This paper introduces a domain-adaptive method for bronchoscopic depth estimation that combines supervised training on synthetic data with unsupervised adversarial adaptation to real images, improving accuracy in challenging tissue textures.

Contribution

The paper presents a novel two-step domain adaptation approach for depth estimation in bronchoscopic images, addressing the scarcity of labeled real data and tissue texture challenges.

Findings

Significant performance improvement on real bronchoscopic images.

Effective integration into 3D reconstruction pipelines.

Demonstrated superiority over existing methods.

Abstract

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.