Investigating Optimal Training and Uncertainty Quantification for CNN-based Optical Flow

Optical Flow (OF) techniques provide “dense estimation” flow maps (i.e. pixel-level resolution) of timecorrelated images and thus are appealing to applications requiring high spatial resolutions. OF methods revolve around mathematical descriptions of the image as a collection of features, in which the pixel-level light intensity is the primary variable (Horn and Schunck, 1981). Feature tracking often involves the notion of scale invariance. Traditional OF approaches, merely based on mathematical formulations, have suffered from many challenges, especially when directly applied to images of fluid flows textured with tracer particles (hereafter PIV-like images). Due to the limited number of computationally manageable features and suboptimal regularization methods, successful implementation of past approaches has been limited to highly textured images and small displacement dynamic ranges.