PairedGTA: Generating Driving Datasets for Controlled Photometric Shift Analysis
Researchers have developed a new framework using a high-fidelity game engine to generate perfectly paired driving datasets. This method modifies illumination and weather conditions while keeping scene geometry and object placement consistent. The generated datasets allow for a more accurate analysis of how photometric shifts affect visual perception systems in autonomous driving, as demonstrated by an evaluation of semantic segmentation models. AI
IMPACT Enables more robust evaluation of AI perception systems in autonomous driving by isolating the impact of lighting and weather.