SLAM based Quasi Dense Reconstruction For Minimally Invasive Surgery Scenes

TL;DR

This paper presents a novel quasi dense reconstruction method for surgical scenes in minimally invasive surgery, leveraging SLAM technology and featureless patch matching to improve scene understanding for guidance and augmented reality.

Contribution

It introduces a new approach that converts sparse SLAM maps into quasi dense reconstructions using correlation-based patch matching, validated with live experiments.

Findings

Achieved a Root Mean Squared Error of 4.9mm in validation

Successfully converted sparse SLAM maps to quasi dense reconstructions

Validated approach with live porcine experiment

Abstract

Recovering surgical scene structure in laparoscope surgery is crucial step for surgical guidance and augmented reality applications. In this paper, a quasi dense reconstruction algorithm of surgical scene is proposed. This is based on a state-of-the-art SLAM system, and is exploiting the initial exploration phase that is typically performed by the surgeon at the beginning of the surgery. We show how to convert the sparse SLAM map to a quasi dense scene reconstruction, using pairs of keyframe images and correlation-based featureless patch matching. We have validated the approach with a live porcine experiment using Computed Tomography as ground truth, yielding a Root Mean Squared Error of 4.9mm.