On Optical Flow Models for Variational Motion Estimation
This work addresses the challenge of accurate motion estimation in computer vision, which is crucial for applications like video analysis, but it is incremental as it builds on existing regularization techniques.
The paper tackles the problem of evaluating and improving variational optical flow models for motion estimation by comparing total variation regularization methods with different data fidelities and extensions like Bregman iterations, resulting in a quantitative analysis using various quality measures to assess performance.
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.