Geometry-Aware Camera Localization for Bronchoscopy

2026-08-07

AI Summary

Bronchoscopy poses significant challenges for millimeter-level camera localization due to complex anatomy, scarce data, and stringent real-time requirements. To address this, this work proposes the Geometry-Aware Bronchoscopic Localization (GABL) framework, which integrates preoperative structural priors with intraoperative video to estimate 6-degree-of-freedom pose through a graph-guided coarse-to-fine strategy. GABL combines a Transformer-based tracking model with a novel RGB-depth matching objective, enforcing spatiotemporal and geometric consistency constraints. The method introduces a graph neural network-driven structural prior mechanism and a multimodal matching objective, effectively mitigating visual ambiguity and pose jitter. Experiments demonstrate that GABL reduces translation error by 8.37% and rotation error by 31.76% compared to the state-of-the-art, while achieving a real-time inference speed of 33.6 FPS—four times faster—thus fulfilling the demands of high-precision, real-time bronchoscopic navigation.

Abstract

Camera localization in bronchoscopy remains a challenging problem due to stringent accuracy requirements, real-time constraints, and limited training data. Compared to natural scenes, the confined anatomical structures demand millimeter-level precision, while intraoperative guidance necessitates low-latency inference. However, existing methods often fail to effectively exploit preoperative geometric priors, limiting their robustness and accuracy. To address these limitations, we propose a unified geometry-aware bronchoscope localization framework (GABL) that effectively fuses preoperative structural priors with paired intraoperative video to estimate 6-DoF camera poses. Specifically, to address visual ambiguity in complex airways, we propose a graph-guided coarse-to-fine localization scheme that effectively leverages structural priors for precise pose estimation. Furthermore, to mitigate pose jitter and bridge the visual-structural gap, we integrate a Transformer-based tracking model with a novel RGB-depth matching objective, jointly enforcing spatio-temporal and geometric consistency. Extensive experiments demonstrate that our method yields remarkable reductions of 8.37% and 31.76% in translation and rotation errors over the prior state-of-the-art, alongside 4 times inference speedup (33.6 FPS) for robust real-time bronchoscope localization. Project website: https://paulili08.github.io/GABL/.

Problem

• camera localization
• bronchoscopy
• geometry-aware
• preoperative priors
• 6-DoF pose estimation

Innovation

• geometry-aware localization
• graph-guided pose estimation
• Transformer-based tracking
• RGB-depth matching
• bronchoscopy navigation