Search Results for author:
Found 18 papers, 0 papers with code
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.
Generalised Probabilistic Diffusion Scale-Spaces
In order to shed light on these connections to classical image filtering, we propose a generalised scale-space theory for probabilistic diffusion models.
Efficient Neural Generation of 4K Masks for Homogeneous Diffusion Inpainting
It trains a mask generation network with the help of a neural inpainting surrogate.
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.
Generalised Scale-Space Properties for Probabilistic Diffusion Models
Probabilistic diffusion models enjoy increasing popularity in the deep learning community.
Deep Spatial and Tonal Data Optimisation for Homogeneous Diffusion Inpainting
This provides real-time performance with high quality results.
A Wasserstein GAN for Joint Learning of Inpainting and Spatial Optimisation
However, a carefully selected mask of known pixels that yield a high quality inpainting can also act as a sparse image representation.
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.
Translating Numerical Concepts for PDEs into Neural Architectures
We investigate what can be learned from translating numerical algorithms into neural networks.
Quantisation Scale-Spaces
Recently, sparsification scale-spaces have been obtained as a sequence of inpainted images by gradually removing known image data.
JPEG Meets PDE-based Image Compression
Our codec consistently outperforms JPEG and gives useful indications for successfully developing hybrid codecs further.
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.
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.
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.
Clustering-Based Quantisation for PDE-Based Image Compression
We are lead to the central question which kind of feature vectors are best suited for image compression.
