Search Results for author:
Found 34 papers, 1 papers with code
Efficient Parallel Algorithms for Inpainting-Based Representations of 4K Images -- Part II: Spatial and Tonal Data Optimization
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.
Efficient Parallel Algorithms for Inpainting-Based Representations of 4K Images -- Part I: Homogeneous Diffusion Inpainting
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.
Gaining Insights into Denoising by Inpainting
In contrast to traditional denoising methods that adapt the operator to the data, our approach adapts the data to the operator.
Regularised Diffusion-Shock Inpainting
We introduce regularised diffusion--shock (RDS) inpainting as a modification of diffusion--shock inpainting from our SSVM 2023 conference paper.
Anisotropic Diffusion Stencils: From Simple Derivations over Stability Estimates to ResNet Implementations
Our directional splitting also allows a very natural translation of the explicit scheme into ResNet blocks.
Efficient Neural Generation of 4K Masks for Homogeneous Diffusion Inpainting
It trains a mask generation network with the help of a neural inpainting surrogate.
Diffusion-Shock Inpainting
Moreover, it benefits from the sharp edge structure generated by the shock filter, and it exploits the efficient filling-in effect of homogeneous diffusion.
Image Blending with Osmosis
For our blending purposes, we explore several ways to compose drift vector fields based on the derivatives of our input images.
Optimising Different Feature Types for Inpainting-based Image Representations
Its performance is demonstrated with a novel set of features that also includes local averages.
Deep Spatial and Tonal Data Optimisation for Homogeneous Diffusion Inpainting
This provides real-time performance with high quality results.
Stabilised Inverse Flowline Evolution for Anisotropic Image Sharpening
However, backward diffusion is highly ill-posed.
CNN-based Euler's Elastica Inpainting with Deep Energy and Deep Image Prior
As a remedy, we design the first neural algorithm that simulates inpainting with Euler's Elastica.
Domain Decomposition Algorithms for Real-time Homogeneous Diffusion Inpainting in 4K
Inpainting-based compression methods are qualitatively promising alternatives to transform-based codecs, but they suffer from the high computational cost of the inpainting step.
Learning Sparse Masks for Diffusion-based Image Inpainting
Diffusion-based inpainting is a powerful tool for the reconstruction of images from sparse data.
Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods
With only a few small filters, they can achieve the same invariance as existing techniques which require a fine-grained sampling of orientations.
Connections between Numerical Algorithms for PDEs and Neural Networks
We connect these concepts to residual networks, recurrent neural networks, and U-net architectures.
Efficient Data Optimisation for Harmonic Inpainting with Finite Elements
Harmonic inpainting with optimised data is very popular for inpainting-based image compression.
Translating Numerical Concepts for PDEs into Neural Architectures
We investigate what can be learned from translating numerical algorithms into neural networks.
Multi-frame Super-resolution from Noisy Data
Obtaining high resolution images from low resolution data with clipped noise is algorithmically challenging due to the ill-posed nature of the problem.
JPEG Meets PDE-based Image Compression
Our codec consistently outperforms JPEG and gives useful indications for successfully developing hybrid codecs further.
Sparse Inpainting with Smoothed Particle Hydrodynamics
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.
A Systematic Evaluation of Coding Strategies for Sparse Binary Images
Inpainting-based compression represents images in terms of a sparse subset of its pixel data.
Learning Integrodifferential Models for Image Denoising
We show that both multiscale information and anisotropy are crucial for its success.
Inpainting-based Video Compression in FullHD
Compression methods based on inpainting are an evolving alternative to classical transform-based codecs for still images.
Translating Diffusion, Wavelets, and Regularisation into Residual Networks
Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood.
Removing Multi-frame Gaussian Noise by Combining Patch-based Filters with Optical Flow
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.
Robustness of Brain Tumor Segmentation
In our work we investigate the generalization behavior of deep neural networks in this scenario.
Variational Coupling Revisited: Simpler Models, Theoretical Connections, and Novel Applications
As a specific example, we present a first order coupling model that outperforms classical TV regularisation.
Learning a Generic Adaptive Wavelet Shrinkage Function for Denoising
In contrast to many existing shrinkage functions, it is able to enhance image structures by amplifying wavelet coefficients.
Object Segmentation Tracking from Generic Video Cues
Our simple method can provide competitive results compared to the costly CNN-based methods with parameter tuning.
Stable Backward Diffusion Models that Minimise Convex Energies
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.
Anisotropic osmosis filtering for shadow removal in images
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,
Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting
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.
Optimising Spatial and Tonal Data for PDE-based Inpainting
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.
