Fast Piecewise-Affine Motion Estimation Without Segmentation

TL;DR

This paper introduces a segmentation-free, efficient method for piecewise affine motion estimation that directly estimates motion fields with competitive accuracy and lower computational cost, outperforming traditional segmentation-based approaches.

Contribution

A novel direct estimation approach for piecewise affine motion fields that avoids segmentation and uses a new regularization scheme, reducing complexity and computational cost.

Findings

No initialization needed for the proposed method.

Lower computational cost independent of motion complexity.

Competitive accuracy on standard benchmarks.

Abstract

Current algorithmic approaches for piecewise affine motion estimation are based on alternating motion segmentation and estimation. We propose a new method to estimate piecewise affine motion fields directly without intermediate segmentation. To this end, we reformulate the problem by imposing piecewise constancy of the parameter field, and derive a specific proximal splitting optimization scheme. A key component of our framework is an efficient one-dimensional piecewise-affine estimator for vector-valued signals. The first advantage of our approach over segmentation-based methods is its absence of initialization. The second advantage is its lower computational cost which is independent of the complexity of the motion field. In addition to these features, we demonstrate competitive accuracy with other piecewise-parametric methods on standard evaluation benchmarks. Our new regularization scheme also outperforms the more standard use of total variation and total generalized variation.