- 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
- full text manuscript: PDF low-res. (1.5MB) PDF (17.4MB) [?]
- source code: TAR/GZ
History
- Note from the editor: the original source code was modified on 2021-10-13 to update the requeriments.txt file for the setup of the python environment. The original version of the code is available here.
- Note from the editor: the manuscript of the article was modified on 2022-01-01 to include information about its editors. The original version of the manuscript is available here.