Scene Adaptive Cosmetic Makeup Transfer

Rishubh Parihar, Aniket Dashpute, Prem Kalra

Abstract: Cosmetic makeup is an art in itself which people use to often enhance their beauty and express themselves. Putting on makeup is a tedious task, so who would not love to see themselves in makeup before physically applying it? In this work, we demonstrate the transfer of makeup from a reference makeup image to some subject image. Our technique involves generation and use of 3D face models of these images. Some nice features of our pipeline include: (1) process adapts to the lighting conditions of the subject image. (2) after makeup on subject image, it is possible to view it in different indoor and outdoor lighting conditions. (3) accessories can be added realistically with proper lighting so that they naturally fit in the subject's scene. Experiments show that these also make our makeup look very realistic and improved compared to many existing frameworks. The main advantage of our novel pipeline is the requirement of only the subject and reference images as input. This is unlike other techniques using 3D models which require extensive data collection.