Improving feature stability during upsampling–spectral artifacts and the importance of spatial context
S Agnihotri, J Grabinski, M Keuper - European Conference on Computer …, 2025 - Springer
Pixel-wise predictions are required in a wide variety of tasks such as image restoration,
image segmentation, or disparity estimation. Common models involve several stages of data …
image segmentation, or disparity estimation. Common models involve several stages of data …
Beware of Aliases--Signal Preservation is Crucial for Robust Image Restoration
Image restoration networks are usually comprised of an encoder and a decoder, responsible
for aggregating image content from noisy, distorted data and to restore clean, undistorted …
for aggregating image content from noisy, distorted data and to restore clean, undistorted …
Variable layout CMOS pixels for end-to-end learning in task specific image sensors
B Choubey, H Sommerhoff, M Moeller… - 2024 IEEE 6th …, 2024 - ieeexplore.ieee.org
CMOS Image Sensors produce data used in several machine learning models. Typically,
their layout is limited to rectangular grid of uniform pixels. However, their shape and size can …
their layout is limited to rectangular grid of uniform pixels. However, their shape and size can …
Roll the dice: Monte Carlo Downsampling as a low-cost Adversarial Defence
S Agnihotri, S Priyadarshi, H Sommerhoff, J Grabinski… - openreview.net
The well-known vulnerability of Neural Networks to adversarial attacks is concerning, more
so with the increasing reliance on them for real-world applications like autonomous driving …
so with the increasing reliance on them for real-world applications like autonomous driving …