Enhancing Bronchoscopy Depth Estimation through Synthetic-to-Real Domain Adaptation

TL;DR

This work proposes a transfer learning framework that leverages synthetic data with depth labels for training and adapts domain knowledge for accurate depth estimation in real bronchoscope data, and demonstrates improved depth prediction on real footage using domain adaptation.

Abstract

Monocular depth estimation has shown promise in general imaging tasks, aiding in localization and 3D reconstruction. While effective in various domains, its application to bronchoscopic images is hindered by the lack of labeled data, challenging the use of supervised learning methods. In this work, we propose a transfer learning framework that leverages synthetic data with depth labels for training and adapts domain knowledge for accurate depth estimation in real bronchoscope data. Our network demonstrates improved depth prediction on real footage using domain adaptation compared to training solely on synthetic data, validating our approach.

Figures (2)

• Figure 1: Diagram of the Synthetic-to-Real Domain Adaptation pipeline.
• Figure 2: Quantitative Evaluation on Real Bronchoscopy Data.$\bigtriangleup$ denotes absolute error ranging from lowest (blue) to highest (red).