Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow

TL;DR

This paper introduces a two-step aggregation method for optical flow that combines local parametric motion candidates with exemplar-based occlusion handling, achieving state-of-the-art results especially with large displacements and occlusions.

Contribution

A novel two-step aggregation framework that jointly estimates optical flow and occlusions using local parametric candidates and exemplar-based occlusion filling.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Significant improvements in large displacement and occlusion scenarios.

Effective joint estimation of flow and occlusion maps.

Abstract

Handling all together large displacements, motion details and occlusions remains an open issue for reliable computation of optical flow in a video sequence. We propose a two-step aggregation paradigm to address this problem. The idea is to supply local motion candidates at every pixel in a first step, and then to combine them to determine the global optical flow field in a second step. We exploit local parametric estimations combined with patch correspondences and we experimentally demonstrate that they are sufficient to produce highly accurate motion candidates. The aggregation step is designed as the discrete optimization of a global regularized energy. The occlusion map is estimated jointly with the flow field throughout the two steps. We propose a generic exemplar-based approach for occlusion filling with motion vectors. We achieve state-of-the-art results in computer vision benchmarks, with particularly significant improvements in the case of large displacements and occlusions.