Learning Energy Based Inpainting for Optical Flow

Publikation: KonferenzbeitragPaperForschungBegutachtung

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 - Perth Western Australia, Perth, Australien
Dauer: 4 Dez 20186 Dez 2018
http://accv2018.net

Konferenz

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

Fingerprint

Optical flows
Feature extraction
Neural networks
Data storage equipment

Schlagwörter

    Dies zitieren

    Vogel, C., Knöbelreiter, P., & Pock, T. (2018). Learning Energy Based Inpainting for Optical Flow. Beitrag in 14th Asian Conference on Computer Vision, Perth, Australien.

    Learning Energy Based Inpainting for Optical Flow. / Vogel, Christoph; Knöbelreiter, Patrick; Pock, Thomas.

    2018. Beitrag in 14th Asian Conference on Computer Vision, Perth, Australien.

    Publikation: KonferenzbeitragPaperForschungBegutachtung

    Vogel, C, Knöbelreiter, P & Pock, T 2018, 'Learning Energy Based Inpainting for Optical Flow' Beitrag in, Perth, Australien, 4/12/18 - 6/12/18, .
    Vogel C, Knöbelreiter P, Pock T. Learning Energy Based Inpainting for Optical Flow. 2018. Beitrag in 14th Asian Conference on Computer Vision, Perth, Australien.
    Vogel, Christoph ; Knöbelreiter, Patrick ; Pock, Thomas. / Learning Energy Based Inpainting for Optical Flow. Beitrag in 14th Asian Conference on Computer Vision, Perth, Australien.
    @conference{88811ea9f7f84656a7a2d93ee60ff201,
    title = "Learning Energy Based Inpainting for Optical Flow",
    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.",
    keywords = "Optical Flow, Energy Optimization, Deep Learning",
    author = "Christoph Vogel and Patrick Kn{\"o}belreiter and Thomas Pock",
    year = "2018",
    month = "12",
    day = "4",
    language = "English",
    note = "14th Asian Conference on Computer Vision, ACCV 2018 ; Conference date: 04-12-2018 Through 06-12-2018",
    url = "http://accv2018.net",

    }

    TY - CONF

    T1 - Learning Energy Based Inpainting for Optical Flow

    AU - Vogel, Christoph

    AU - Knöbelreiter, Patrick

    AU - Pock, Thomas

    PY - 2018/12/4

    Y1 - 2018/12/4

    N2 - 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.

    AB - 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.

    KW - Optical Flow

    KW - Energy Optimization

    KW - Deep Learning

    M3 - Paper

    ER -