On Optical Flow Models for Variational Motion Estimation

TL;DR

This paper evaluates total variation regularization methods for optical flow-based motion estimation, comparing different variants and optimization techniques, and emphasizes the importance of quantitative evaluation of motion estimation quality.

Contribution

It provides a comprehensive overview of total variation regularization variants, introduces Bregman iterations, and discusses quantitative evaluation methods for optical flow models.

Findings

Total variation regularization improves motion estimation accuracy.

Bregman iterations enhance the robustness of variational models.

Quantitative measures are crucial for evaluating optical flow quality.

Abstract

The aim of this paper is to discuss and evaluate total variation based regularization methods for motion estimation, with particular focus on optical flow models. In addition to standard $L^2$ and $L^1$ data fidelities we give an overview of different variants of total variation regularization obtained from combination with higher order models and a unified computational optimization approach based on primal-dual methods. Moreover, we extend the models by Bregman iterations and provide an inverse problems perspective to the analysis of variational optical flow models. A particular focus of the paper is the quantitative evaluation of motion estimation, which is a difficult and often underestimated task. We discuss several approaches for quality measures of motion estimation and apply them to compare the previously discussed regularization approaches.