Paper accepted at WACV 2026

Our paper “Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?” has been accepted to WACV 2026. Authors: Annika Muetze, Sadia Ilyas, Christian Dörpelkus, and Matthias Rottmann.

This work builds on Christian Dörpelkus Master’s thesis and marks a strong step forward in our research on evaluating open-vocabulary vision models with generated data. After a second submission, the paper was accepted, showing that the extra effort and persistence paid off.

Congratulations to everyone involved for the result and the work behind it.