Learning Energy Based Inpainting for Optical Flow

Christoph Vogel, Patrick Knöbelreiter, Thomas Pock

Publikation: KonferenzbeitragPaperBegutachtung


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.
PublikationsstatusVeröffentlicht - 4 Dez 2018
Veranstaltung14th Asian Conference on Computer Vision: ACCV 2018 - Perth Western Australia, Perth, Australien
Dauer: 4 Dez 20186 Dez 2018


Konferenz14th Asian Conference on Computer Vision
KurztitelACCV 2018


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

Dieses zitieren