no code implementations • ICLR 2019 • Michael Grunwald, Matthias Hermann, Fabian Freiberg, Matthias O. Franz
Based on a dig- ital print inspection scenario we show that psychophysical texture representations are able to outperform CNN-encoded features.
no code implementations • 8 Dec 2017 • Pascal Laube, Michael Grunwald, Matthias O. Franz, Georg Umlauf
In this work we propose the use of convolutional neural networks (CNN) for image inpainting of large regions in high-resolution textures.
no code implementations • 3 Nov 2016 • Vania V. Estrela, Matthias O. Franz, Ricardo T. Lopes, G. P. De Araujo
It relies on the use of a data-driven technique called Mixed Norm (MN) to estimate the best motion vector for a given pixel.