Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling

TL;DR

This paper introduces a novel framework for monocular endoscopic depth estimation that incorporates geometric modeling to recover absolute scale and improve detail accuracy, validated on real and simulated data.

Contribution

It proposes a multi-resolution depth fusion and geometric scale recovery method that enhances monocular depth estimation with absolute scale in endoscopic scenes.

Findings

Effective scale recovery from monocular images.

Improved depth detail accuracy on tissue and instruments.

Validated on real and simulated endoscopic data.

Abstract

Scale-aware monocular depth estimation poses a significant challenge in computer-aided endoscopic navigation. However, existing depth estimation methods that do not consider the geometric priors struggle to learn the absolute scale from training with monocular endoscopic sequences. Additionally, conventional methods face difficulties in accurately estimating details on tissue and instruments boundaries. In this paper, we tackle these problems by proposing a novel enhanced scale-aware framework that only uses monocular images with geometric modeling for depth estimation. Specifically, we first propose a multi-resolution depth fusion strategy to enhance the quality of monocular depth estimation. To recover the precise scale between relative depth and real-world values, we further calculate the 3D poses of instruments in the endoscopic scenes by algebraic geometry based on the image-only geometric primitives (i.e., boundaries and tip of instruments). Afterwards, the 3D poses of surgical instruments enable the scale recovery of relative depth maps. By coupling scale factors and relative depth estimation, the scale-aware depth of the monocular endoscopic scenes can be estimated. We evaluate the pipeline on in-house endoscopic surgery videos and simulated data. The results demonstrate that our method can learn the absolute scale with geometric modeling and accurately estimate scale-aware depth for monocular scenes.