activity
20242026
collaborators

8 papers

cs.CV2026

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration

Shashank Agnihotri, Julia Grabinski, Janis Keuper +1

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…

cs.CV2026

Deepfakes: we need to re-think the concept of "real" images

Janis Keuper, Margret Keuper

The wide availability and low usability barrier of modern image generation models has triggered the reasonable fear of criminal misconduct and negative social implications. The mac…

cs.CV2025

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling

Julia Grabinski, Steffen Jung, Janis Keuper +1

Convolutional Neural Networks (CNNs) are successful in various computer vision tasks. From an image and signal processing point of view, this success is counter-intuitive, as the i…

cs.CV2025

Can We Talk Models Into Seeing the World Differently?

Paul Gavrikov, Jovita Lukasik, Steffen Jung +4

Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model…

cs.CV2024

How Do Training Methods Influence the Utilization of Vision Models?

Paul Gavrikov, Shashank Agnihotri, Margret Keuper +1

Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values…

cs.CV2024

Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail

Bianca Lamm, Janis Keuper

Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and…