Continuous Parametric Optical Flow

Jianqin Luo, Zhexiong Wan, yuxin mao, Bo Li, Yuchao Dai

Keywords: optical flow, point trajectories, continuous motion, neural ordinary differential equation

TL;DR: A temporal-parametric model based on B-splines to utilize limited visible frames to fit point trajectory and output the parametric continuous optical flow

Abstract: In this paper, we present continuous parametric optical flow, a parametric representation of dense and continuous motion over arbitrary time interval. In contrast to existing discrete-time representations (i.e., flow in between consecutive frames), this new representation transforms the frame-to-frame pixel correspondences to dense continuous flow. In particular, we present a temporal-parametric model that employs B-splines to fit point trajectories using a limited number of frames. To further improve the stability and robustness of the trajectories, we also add an encoder with a neural ordinary differential equation (NODE) to represent features associated with specific times. We also contribute a synthetic dataset and introduce two evaluation perspectives to measure the accuracy and robustness of continuous flow estimation. Benefiting from the combination of explicit parametric modeling and implicit feature optimization, our model focuses on motion continuity and outperforms the flow-based and point-tracking approaches for fitting long-term and variable sequences.

Submission Number: 6736