Distilled Visual and Robot Kinematics Embeddings for Metric Depth Estimation in Monocular Scene Reconstruction

TL;DR

This paper introduces a novel deep learning framework that combines robot kinematics and monocular endoscopy to accurately estimate metric depth and reconstruct 3D surgical scenes, overcoming limitations of traditional stereo methods.

Contribution

The authors develop a unified approach integrating robot kinematics, monocular images, and deep learning for precise metric depth estimation and 3D reconstruction in robotic surgery.

Findings

Achieved comparable depth estimation performance to stereo methods on public datasets.

Developed a Depth-driven Sliding Optimization (DDSO) algorithm for scale extraction.

Successfully reconstructed 3D surgical scenes from monocular endoscopic videos.

Abstract

Estimating precise metric depth and scene reconstruction from monocular endoscopy is a fundamental task for surgical navigation in robotic surgery. However, traditional stereo matching adopts binocular images to perceive the depth information, which is difficult to transfer to the soft robotics-based surgical systems due to the use of monocular endoscopy. In this paper, we present a novel framework that combines robot kinematics and monocular endoscope images with deep unsupervised learning into a single network for metric depth estimation and then achieve 3D reconstruction of complex anatomy. Specifically, we first obtain the relative depth maps of surgical scenes by leveraging a brightness-aware monocular depth estimation method. Then, the corresponding endoscope poses are computed based on non-linear optimization of geometric and photometric reprojection residuals. Afterwards, we develop a Depth-driven Sliding Optimization (DDSO) algorithm to extract the scaling coefficient from kinematics and calculated poses offline. By coupling the metric scale and relative depth data, we form a robust ensemble that represents the metric and consistent depth. Next, we treat the ensemble as supervisory labels to train a metric depth estimation network for surgeries (i.e., MetricDepthS-Net) that distills the embeddings from the robot kinematics, endoscopic videos, and poses. With accurate metric depth estimation, we utilize a dense visual reconstruction method to recover the 3D structure of the whole surgical site. We have extensively evaluated the proposed framework on public SCARED and achieved comparable performance with stereo-based depth estimation methods. Our results demonstrate the feasibility of the proposed approach to recover the metric depth and 3D structure with monocular inputs.