Motion Estimation for Large Displacements and Deformations

TL;DR

HybridFlow is a novel variational motion estimation framework that effectively handles large displacements and deformations in optical flow, outperforming existing methods on benchmark datasets without requiring training.

Contribution

The paper introduces HybridFlow, a multi-scale hybrid matching approach that improves large displacement optical flow estimation by handling deformations and large motions without training.

Findings

HybridFlow outperforms state-of-the-art variational methods on benchmarks.

HybridFlow achieves comparable results to deep-learning techniques.

The approach is robust to large displacements and scene deformations.

Abstract

Large displacement optical flow is an integral part of many computer vision tasks. Variational optical flow techniques based on a coarse-to-fine scheme interpolate sparse matches and locally optimize an energy model conditioned on colour, gradient and smoothness, making them sensitive to noise in the sparse matches, deformations, and arbitrarily large displacements. This paper addresses this problem and presents HybridFlow, a variational motion estimation framework for large displacements and deformations. A multi-scale hybrid matching approach is performed on the image pairs. Coarse-scale clusters formed by classifying pixels according to their feature descriptors are matched using the clusters' context descriptors. We apply a multi-scale graph matching on the finer-scale superpixels contained within each matched pair of coarse-scale clusters. Small clusters that cannot be further subdivided are matched using localized feature matching. Together, these initial matches form the flow, which is propagated by an edge-preserving interpolation and variational refinement. Our approach does not require training and is robust to substantial displacements and rigid and non-rigid transformations due to motion in the scene, making it ideal for large-scale imagery such as Wide-Area Motion Imagery (WAMI). More notably, HybridFlow works on directed graphs of arbitrary topology representing perceptual groups, which improves motion estimation in the presence of significant deformations. We demonstrate HybridFlow's superior performance to state-of-the-art variational techniques on two benchmark datasets and report comparable results with state-of-the-art deep-learning-based techniques.