Motion inpainting by an image-based geodesic AMLE method

Oliver, Maria; Raad, Lara; Ballester, Coloma; Haro Ortega, Gloria

doi:http://dx.doi.org/10.1109/ICIP.2018.8451851

Motion inpainting by an image-based geodesic AMLE method

Citation

Oliver M, Raad L, Ballester C, Haro G. Motion inpainting by an image-based geodesic AMLE method. In: 2018 25th IEEE International Conference on Image Processing (ICIP); 2018 Oct 7-10; Athens, Greece. Piscataway (NJ): IEEE; 2018. p. 2267-71. DOI: 10.1109/ICIP.2018.8451851

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).

Description

Comunicació presentada al congrés 25th IEEE International Conference on Image Processing (ICIP) celebrat del 7 al 10 d'octubre de 2018 a Atenes, Grècia.