Human Visual Perception

Human visual perception research aims to understand how humans see and interpret images, focusing on bridging the gap between human and machine vision. Current research investigates how different color models and perceptual components (color, shape, texture) influence both human and machine interpretation of images, employing various deep learning architectures like Vision Transformers and CNNs, and exploring techniques like foveated rendering and adversarial robustness to improve model performance and alignment with human visual processing. This work has significant implications for improving computer vision systems in applications such as autonomous driving, medical imaging, and image generation, as well as advancing our fundamental understanding of the human visual system.