On Anisotropic Optical Flow Inpainting Algorithms
Lara Raad, Maria Oliver, Coloma Ballester, Gloria Haro, Enric Meinhardt
published
2020-06-28
reference
Lara Raad, Maria Oliver, Coloma Ballester, Gloria Haro, and Enric Meinhardt, On Anisotropic Optical Flow Inpainting Algorithms, Image Processing On Line, 10 (2020), pp. 78–104. https://doi.org/10.5201/ipol.2020.281

Communicated by Luis Álvarez, Agustín Salgado, Nelson Monzón-López
Demo edited by Enric Meinhardt-Llopis, Lara Raad

Abstract

This work describes two anisotropic optical flow inpainting algorithms. The first one recovers the missing flow values using the Absolutely Minimizing Lipschitz Extension partial differential equation (also called infinity Laplacian equation) and the second one uses the Laplace partial differential equation, both defined on a Riemmanian manifold. The Riemannian manifold is defined by endowing the plane domain with an appropriate metric depending on the reference video frame. A detailed analysis of both approaches is provided and their results are compared on three different applications: flow densification, occlusion inpainting and large hole inpainting.

Download

History