Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light
Researchers have developed a method to create synthetic low-light images for evaluating AI pedestrian detection models, particularly for autonomous driving in dark conditions. This technique uses synthetic RAW image augmentation to mimic camera sensor noise, generating samples that are difficult for AI models to distinguish from real low-light data. The approach aims to improve the continuous sampling of the input space and enhance data coverage for better model generalization and performance characterization. AI
IMPACT Enhances AI model evaluation in challenging low-light conditions, crucial for safety-critical applications like autonomous driving.