no code implementations • 12 Jan 2024 • Niklas Kämper, Vassillen Chizhov, Joachim Weickert
Homogeneous diffusion inpainting can reconstruct missing image areas with high quality from a sparse subset of known pixels, provided that their location as well as their gray or color values are well optimized.
no code implementations • 12 Jan 2024 • Niklas Kämper, Vassillen Chizhov, Joachim Weickert
However, a major challenge has been to design fast solvers for homogeneous diffusion inpainting that scale to 4K image resolution ($3840 \times 2160$ pixels) and are real-time capable.
no code implementations • 23 Sep 2023 • Daniel Gaa, Vassillen Chizhov, Pascal Peter, Joachim Weickert, Robin Dirk Adam
In contrast to traditional denoising methods that adapt the operator to the data, our approach adapts the data to the operator.
no code implementations • 15 Sep 2023 • Kristina Schaefer, Joachim Weickert
We introduce regularised diffusion--shock (RDS) inpainting as a modification of diffusion--shock inpainting from our SSVM 2023 conference paper.
no code implementations • 11 Sep 2023 • Karl Schrader, Joachim Weickert, Michael Krause
Our directional splitting also allows a very natural translation of the explicit scheme into ResNet blocks.
no code implementations • 17 Mar 2023 • Karl Schrader, Pascal Peter, Niklas Kämper, Joachim Weickert
It trains a mask generation network with the help of a neural inpainting surrogate.
no code implementations • 16 Mar 2023 • Kristina Schaefer, Joachim Weickert
Moreover, it benefits from the sharp edge structure generated by the shock filter, and it exploits the efficient filling-in effect of homogeneous diffusion.
no code implementations • 14 Mar 2023 • Paul Bungert, Pascal Peter, Joachim Weickert
For our blending purposes, we explore several ways to compose drift vector fields based on the derivatives of our input images.
no code implementations • 26 Oct 2022 • Ferdinand Jost, Vassillen Chizhov, Joachim Weickert
Its performance is demonstrated with a novel set of features that also includes local averages.
no code implementations • 30 Aug 2022 • Pascal Peter, Karl Schrader, Tobias Alt, Joachim Weickert
This provides real-time performance with high quality results.
no code implementations • 20 Jul 2022 • Kristina Schaefer, Joachim Weickert
However, backward diffusion is highly ill-posed.
no code implementations • 16 Jul 2022 • Karl Schrader, Tobias Alt, Joachim Weickert, Michael Ertel
As a remedy, we design the first neural algorithm that simulates inpainting with Euler's Elastica.
no code implementations • 8 Oct 2021 • Niklas Kämper, Joachim Weickert
Inpainting-based compression methods are qualitatively promising alternatives to transform-based codecs, but they suffer from the high computational cost of the inpainting step.
no code implementations • 6 Oct 2021 • Tobias Alt, Pascal Peter, Joachim Weickert
Diffusion-based inpainting is a powerful tool for the reconstruction of images from sparse data.
no code implementations • 31 Aug 2021 • Tobias Alt, Karl Schrader, Joachim Weickert, Pascal Peter, Matthias Augustin
With only a few small filters, they can achieve the same invariance as existing techniques which require a fine-grained sampling of orientations.
no code implementations • 30 Jul 2021 • Tobias Alt, Karl Schrader, Matthias Augustin, Pascal Peter, Joachim Weickert
We connect these concepts to residual networks, recurrent neural networks, and U-net architectures.
no code implementations • 4 May 2021 • Vassillen Chizhov, Joachim Weickert
Harmonic inpainting with optimised data is very popular for inpainting-based image compression.
no code implementations • 29 Mar 2021 • Tobias Alt, Pascal Peter, Joachim Weickert, Karl Schrader
We investigate what can be learned from translating numerical algorithms into neural networks.
no code implementations • 25 Mar 2021 • Kireeti Bodduna, Joachim Weickert
Obtaining high resolution images from low resolution data with clipped noise is algorithmically challenging due to the ill-posed nature of the problem.
no code implementations • 1 Feb 2021 • Sarah Andris, Joachim Weickert, Tobias Alt, Pascal Peter
Our codec consistently outperforms JPEG and gives useful indications for successfully developing hybrid codecs further.
no code implementations • 23 Nov 2020 • Viktor Daropoulos, Matthias Augustin, Joachim Weickert
Furthermore, we examine the use of Voronoi tessellation for defining the necessary parameters in the SPH method as well as selecting optimally located image samples.
no code implementations • 26 Oct 2020 • Rahul Mohideen Kaja Mohideen, Pascal Peter, Joachim Weickert
Inpainting-based compression represents images in terms of a sparse subset of its pixel data.
no code implementations • 21 Oct 2020 • Tobias Alt, Joachim Weickert
We show that both multiscale information and anisotropy are crucial for its success.
no code implementations • 24 Aug 2020 • Sarah Andris, Pascal Peter, Rahul Mohideen Kaja Mohideen, Joachim Weickert, Sebastian Hoffmann
Compression methods based on inpainting are an evolving alternative to classical transform-based codecs for still images.
no code implementations • 7 Feb 2020 • Tobias Alt, Joachim Weickert, Pascal Peter
Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood.
no code implementations • 22 Jan 2020 • Kireeti Bodduna, Joachim Weickert
Patch-based approaches such as 3D block matching (BM3D) and non-local Bayes (NLB) are widely accepted filters for removing Gaussian noise from single-frame images.
no code implementations • 24 Dec 2019 • Sabine Müller, Joachim Weickert, Norbert Graf
In our work we investigate the generalization behavior of deep neural networks in this scenario.
no code implementations • 12 Dec 2019 • Aaron Wewior, Joachim Weickert
As a specific example, we present a first order coupling model that outperforms classical TV regularisation.
no code implementations • 21 Oct 2019 • Tobias Alt, Joachim Weickert
In contrast to many existing shrinkage functions, it is able to enhance image structures by amplifying wavelet coefficients.
no code implementations • 5 Oct 2019 • Amirhossein Kardoost, Sabine Müller, Joachim Weickert, Margret Keuper
Our simple method can provide competitive results compared to the costly CNN-based methods with parameter tuning.
no code implementations • 8 Mar 2019 • Leif Bergerhoff, Marcelo Cárdenas, Joachim Weickert, Martin Welk
Furthermore, we establish a comprehensive theory for the time-continuous evolution and we show that stability carries over to a simple explicit time discretisation of our model.
1 code implementation • 17 Sep 2018 • Simone Parisotto, Luca Calatroni, Marco Caliari, Carola-Bibiane Schönlieb, Joachim Weickert
We present an anisotropic extension of the isotropic osmosis model that has been introduced by Weickert et al.~(Weickert, 2013) for visual computing applications, and we adapt it specifically to shadow removal applications.
Analysis of PDEs 68U10, 94A08, 49K20, 65M06,
no code implementations • 18 Dec 2017 • Tim Dahmen, Patrick Trampert, Pascal Peter, Pinak Bheed, Joachim Weickert, Philipp Slusallek
The approach has the advantage of being agnostic to most modelbased parts of exemplar-based inpainting such as the order in which patches are processed and the cost function used to determine patch similarity.
no code implementations • 15 Jun 2015 • Laurent Hoeltgen, Markus Mainberger, Sebastian Hoffmann, Joachim Weickert, Ching Hoo Tang, Simon Setzer, Daniel Johannsen, Frank Neumann, Benjamin Doerr
Moreover, is more generic than other data optimisation approaches for the sparse inpainting problem, since it can also be extended to nonlinear inpainting operators such as EED.