FaceMap: Distortion-Driven Perceptual Facial Saliency Maps
SessionEnhancing, Saliency
DescriptionHumans are uniquely sensitive to faces. Recognizing fine detail in faces plays an important role in social cognition, identity; and it is key to human interaction. In this work, we present the first quantitative study of the relative importance of face regions to human observers. We created a dataset of 960 unique models featuring localized geometry and texture distortions relevant to visual computing applications. We then conducted an extensive subjective study examining the perceptual saliency of facial regions through the lens of distortion visibility. Our study comprises over 18,000 comparisons and indicates non-trivial preferences across distortion types and facial areas. Our results provide relevant insights for algorithm design, and we demonstrate our data's value in model compression applications.
Event Type
Technical Papers
TimeFriday, 6 December 20242:56pm - 3:08pm JST
LocationHall B5 (2), B Block, Level 5
