BDIS: Bayesian Dense Inverse Searching Method for Real-Time Stereo Surgical Image Matching

Abstract

In stereoscope-based Minimally Invasive Surgeries (MIS), dense stereo matching plays an indispensable role in 3D shape recovery, AR, VR, and navigation tasks. Although numerous Deep Neural Network (DNN) approaches are proposed, the conventional prior-free approaches are still popular in the industry because of the lack of open-source annotated data set and the limitation of the task-specific pre-trained DNNs. Among the prior-free stereo matching algorithms, there is no successful real-time algorithm in none GPU environment for MIS. This paper proposes the first CPU-level real-time priorfree stereo matching algorithm for general MIS tasks. We achieve an average 17 Hz on 640 × 480 images with a singlecore CPU (i5-9400) for surgical images. Meanwhile, it achieves slightly better accuracy than the popular ELAS. The patchbased fast disparity searching algorithm is adopted for the rectified stereo images. A coarse-to-fine Bayesian probability and a spatial Gaussian mixed model were proposed to evaluate the patch probability at different scales. An optional probability density function estimation algorithm was adopted to quantify the prediction variance. Extensive experiments demonstrated the proposed method's capability to handle ambiguities introduced by the textureless surfaces and the photometric inconsistency from the non-Lambertian reflectance and dark illumination. The estimated probability managed to balance the confidences of the patches for stereo images at different scales. It has similar or higher accuracy and fewer outliers than the baseline ELAS in MIS, while it is 4-5 times faster. The code and the synthetic data sets are available at https://github.com/JingweiSong/BDIS-v2.

A Deformation Field-Based Approach for Expression Processing in Head Motion Correction

“…For video based methods, tracking methods are used to calculate the head pose by accumulating the relative transformation between consecutive frames [29]. Typically, the head can be modeled using either an approximate simple geometry or a precise 3D model [30].…”