A Variational Aggregation Framework for Patch-Based Optical Flow Estimation

Denis Fortun (1) , Patrick Bouthemy (1) , Charles Kervrann (1)

1 SERPICO - Space-timE RePresentation, Imaging and cellular dynamics of molecular COmplexes

We propose a variational aggregation method for optical flow estimation. It consists of a two-step framework, first estimating a collection of parametric motion models to generate motion candidates, and then reconstructing a global dense motion field. The aggregation step is designed as a motion reconstruction problem from spatially varying sets of motion candidates given by parametric motion models. Our method is designed to capture large displacements in a variational framework without requiring any coarse-to-fine strategy. We handle occlusion with a motion inpainting approach in the candidates computation step. By performing parametric motion estimation, we combine the robustness to noise of local parametric methods with the accuracy yielded by global regularization. We demonstrate the performance of our aggregation approach by comparing it to standard variational methods and a discrete aggregation approach on the Middlebury and MPI Sintel datasets.

Mots clés: Optical flow; parametric motion; aggregation; variational optimization

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Denis Fortun, Patrick Bouthemy, Charles Kervrann. A Variational Aggregation Framework for Patch-Based Optical Flow Estimation. Journal of Mathematical Imaging and Vision, 2016, 56, pp.280 - 299. ⟨10.1007/s10851-016-0664-6⟩. ⟨hal-01408771⟩