Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example

TL;DR

This paper presents a deep graphics encoder that enables real-time virtual makeup synthesis from a reference image, facilitating automatic and realistic makeup try-on and creation.

Contribution

It introduces an inverse graphics approach that learns to map makeup images to rendering parameters, enabling automatic and realistic virtual makeup synthesis.

Findings

Achieves real-time virtual makeup rendering.

Allows automatic extraction of makeup styles from reference images.

Supports both artist-driven and consumer virtual try-on applications.

Abstract

While makeup virtual-try-on is now widespread, parametrizing a computer graphics rendering engine for synthesizing images of a given cosmetics product remains a challenging task. In this paper, we introduce an inverse computer graphics method for automatic makeup synthesis from a reference image, by learning a model that maps an example portrait image with makeup to the space of rendering parameters. This method can be used by artists to automatically create realistic virtual cosmetics image samples, or by consumers, to virtually try-on a makeup extracted from their favorite reference image.