Aktivitäten pro Jahr
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.
|Publikationsstatus||Veröffentlicht - 4 Dez 2018|
|Veranstaltung||14th Asian Conference on Computer Vision: ACCV 2018 - Perth Western Australia, Perth, Australien|
Dauer: 4 Dez 2018 → 6 Dez 2018
|Konferenz||14th Asian Conference on Computer Vision|
|Zeitraum||4/12/18 → 6/12/18|