# Understanding Beauty via Deep Facial Features

arXiv: https://arxiv.org/abs/1902.05380 · HTML: https://mlsanity.com/paper/1902.05380/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [DeepBlur: A Simple and Effective Method for Natural Image Obfuscation](https://mlsanity.com/paper/2104.02655/) (2021)
- [Interpreting Face Inference Models using Hierarchical Network Dissection](https://mlsanity.com/paper/2108.10360/) (2021)
- [Diffusion-based Facial Aesthetics Enhancement with 3D Structure Guidance](https://mlsanity.com/paper/2503.14402/) (2025)
- [Mitigating Bias in Facial Analysis Systems by Incorporating Label Diversity](https://mlsanity.com/paper/2204.06364/) (2022)
- [Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning](https://mlsanity.com/paper/2208.04517/) (2022)
- [Facial beauty prediction fusing transfer learning and broad learning system](https://mlsanity.com/paper/2603.16930/) (2026)

## Abstract (arXiv)

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.