3 papers
eess.SP2026
The Neural Echo: A Signal Processing Perspective for Understanding Neural Networks
Chongbiao Wang, Daniel Gaa, Joachim Weickert +1
We introduce the neural echo as a tool for understanding the behavior of neural networks. It generalizes the model-based concepts of impulse responses, diffusion echoes, and filter…
eess.IV2025
The Filter Echo: A General Tool for Filter Visualisation
Daniel Gaa, Joachim Weickert, Iva Farag +1
To select suitable filters for a task or to improve existing filters, a deep understanding of their inner workings is vital. Diffusion echoes, which are space-adaptive impulse resp…
eess.IV2023
Connecting Image Inpainting with Denoising in the Homogeneous Diffusion Setting
Daniel Gaa, Vassillen Chizhov, Pascal Peter +2
While local methods for image denoising and inpainting may use similar concepts, their connections have hardly been investigated so far. The goal of this work is to establish links…