5 papers
Translating Numerical Concepts for PDEs into Neural Architectures
Tobias Alt, Pascal Peter, Joachim Weickert +1
We investigate what can be learned from translating numerical algorithms into neural networks. On the numerical side, we consider explicit, accelerated explicit, and implicit schem…
JPEG Meets PDE-based Image Compression
Sarah Andris, Joachim Weickert, Tobias Alt +1
Inpainting-based image compression is emerging as a promising competitor to transform-based compression techniques. Its key idea is to reconstruct image information from only few k…
Compressing Colour Images with Joint Inpainting and Prediction
Rahul Mohideen Kaja Mohideen, Pascal Peter, Tobias Alt +2
Inpainting-based codecs store sparse, quantised pixel data directly and decode by interpolating the discarded image parts. This interpolation can be used simultaneously for efficie…
Translating Diffusion, Wavelets, and Regularisation into Residual Networks
Tobias Alt, Joachim Weickert, Pascal Peter
Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood. To address this problem, we consider the simple prototypical problem of signal de…
Learning a Generic Adaptive Wavelet Shrinkage Function for Denoising
Tobias Alt, Joachim Weickert
The rise of machine learning in image processing has created a gap between trainable data-driven and classical model-driven approaches: While learning-based models often show super…