Real-Time 3D Reconstruction in Minimally Invasive Surgery with Quasi-Dense Matching

In this work, a method for 3D reconstruction of Minimally Invasive Surgery data in real-time is presented. It is formulated on top of the already established framework of Quasi-Dense Matching, optimizing its components for speed. First, it recovers a set of sparse features, which are matched robustly. Then, 3D information is propagated in a spatial neighbourhood, until similarity reaches a predefined threshold, to cover a semi-dense portion of operating field domain. Matching on dense level is achieved with Zero Mean Normalized Cross Correlation metric to establish correspondences. The algorithm is able to recover disparity maps with relatively small error, while maintaining real-time performance.