Understanding Beauty via Deep Facial Features
This work addresses the challenge of subjective beauty definitions for applications in psychology and computer vision, though it is incremental as it builds on existing deep learning methods.
The paper tackled the problem of objectively quantifying facial beauty by mining correlations between deep facial features and attractiveness scores on large datasets, finding that attributes like small nose and high cheekbones contribute to attractiveness and demonstrating beauty enhancements via GAN synthesis validated by a user survey of 10,000 data points.
The concept of beauty has been debated by philosophers and psychologists for centuries, but most definitions are subjective and metaphysical, and deficit in accuracy, generality, and scalability. In this paper, we present a novel study on mining beauty semantics of facial attributes based on big data, with an attempt to objectively construct descriptions of beauty in a quantitative manner. We first deploy a deep convolutional neural network (CNN) to extract facial attributes, and then investigate correlations between these features and attractiveness on two large-scale datasets labelled with beauty scores. Not only do we discover the secrets of beauty verified by statistical significance tests, our findings also align perfectly with existing psychological studies that, e.g., small nose, high cheekbones, and femininity contribute to attractiveness. We further leverage these high-level representations to original images by a generative adversarial network (GAN). Beauty enhancements after synthesis are visually compelling and statistically convincing verified by a user survey of 10,000 data points.