On Anisotropic Optical Flow Inpainting Algorithms
Open Access
- 28 June 2020
- journal article
- research article
- Published by Image Processing On Line in Image Processing On Line
- Vol. 10, 78-104
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.Keywords
This publication has 14 references indexed in Scilit:
- Nonlocal Inpainting of Manifold-Valued Data on Finite Weighted Graphs2017
- A Naturalistic Open Source Movie for Optical Flow Evaluation2012
- Edge-based compression of cartoon-like images with homogeneous diffusionPattern Recognition, 2011
- An axiomatic approach to scalar data interpolation on surfacesNumerische Mathematik, 2005
- A convergent difference scheme for the infinity Laplacian: construction of absolutely minimizing Lipschitz extensionsMathematics of Computation, 2004
- A tour of the theory of absolutely minimizing functionsBulletin of the American Mathematical Society, 2004
- Interpolation of digital elevation models using AMLE and related methodsIEEE Transactions on Geoscience and Remote Sensing, 2002
- An axiomatic approach to image interpolationIEEE Transactions on Image Processing, 1998
- Uniqueness of Lipschitz extensions: Minimizing the sup norm of the gradientArchive for Rational Mechanics and Analysis, 1993
- Extension of functions satisfying lipschitz conditionsArkiv för Matematik, 1967