Learning Energy Based Inpainting for Optical Flow

Christoph Vogel, Patrick Knöbelreiter, Thomas Pock

Publikation: KonferenzbeitragPaperBegutachtung

Abstract

Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze. In this work we seek for a plain, interpretable, but learnable solution. We propose a novel inpainting based algorithm that approaches the problem in three steps: feature selection and matching, selection of supporting points and energy based inpainting. To facilitate the inference we propose an optimization layer that allows to backpropagate through 10K iterations of a first-order method without any numerical or memory problems. Compared to recent state-of-the-art networks, our modular CNN is very lightweight and competitive with other, more involved, inpainting based methods.
Originalspracheenglisch
PublikationsstatusVeröffentlicht - 4 Dez 2018
Veranstaltung14th Asian Conference on Computer Vision: ACCV 2018 - Perth Western Australia, Perth, Australien
Dauer: 4 Dez 20186 Dez 2018
http://accv2018.net

Konferenz

Konferenz14th Asian Conference on Computer Vision
KurztitelACCV 2018
Land/GebietAustralien
OrtPerth
Zeitraum4/12/186/12/18
Internetadresse

Fingerprint

Untersuchen Sie die Forschungsthemen von „Learning Energy Based Inpainting for Optical Flow“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren