works on

From the 1 of 25 linked papers with an AI index.

activity
20242026
collaborators

25 papers

cs.CV2026

Improved Robustness from Biologically Inspired Sparse Contrast Representations

Lorena Stracke, Lia Nimmermann, Shashank Agnihotri +3

The paper introduces a fixed, model‑agnostic preprocessing step inspired by retinal processing that applies color remapping and local contrast extraction to create sparse image rep…

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

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition

Jiawen Xu, Margret Keuper

Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within the realm of deep learning, neural…

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.CV2026

RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo

Victor Oei, Jenny Schmalfuss, Lukas Mehl +5

Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hen…

cs.CV2026

RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images

Mishal Fatima, Shashank Agnihotri, Kanchana Vaishnavi Gandikota +2

Most vision models are trained on RGB images processed through ISP pipelines optimized for human perception, which can discard sensor-level information useful for machine reasoning…