Sorry, you need to enable JavaScript to visit this website.

Motion Inpainting by an Image-Based Geodesic AMLE Method

Primary tabs

Citation Author(s):
Gloria Haro, Coloma Ballester
Submitted by:
Lara Raad
Last updated:
4 October 2018 - 9:30am
Document Type:
Poster
Document Year:
2018
Event:
Presenters Name:
Lara Raad
Paper Code:
2789

Abstract 

Abstract: 

This work presents an automatic method for optical flow inpainting. Given a video, each frame domain is endowed with a Riemannian metric based on the video pixel values. The missing optical flow is recovered by solving the Absolutely Minimizing Lipschitz Extension (AMLE) partial differential equation on the Riemannian manifold. An efficient numerical algorithm is proposed using eikonal operators for nonlinear elliptic partial differential equations on a finite graph. The choice of the metric is discussed and the method is applied to optical flow inpainting and sparse-to-dense optical flow estimation, achieving top-tier performance in terms of End-Point-Error (EPE).

up
0 users have voted:

Dataset Files

poster_icip18.pdf

(165)