Makeup-Go

[poster] [report] [code]
Course project at UM (Nov. - Dec. 2018): Mark Jin, Yi Wen, Yehu Chen, Zixuan Li, Haoxiang Wu
EECS 442: Computer Vision, Instructed by: Jason Corso

Advance of image processing APPs gives rise to an overwhelming trend of artificial beautification. Our project aims to reverse the portrait beautification despite lack of information of the exact process applied. To precisely capture the subtle features of facial images, we apply Principle Component Analysis to the residual images of the original and beautified images, and then train several independent convolutional neural networks to regress each normalized components, and finally restore the original faces.

Dataset

We used the web crawler and portraitbeautifying APPs to build our own dataset.

Architecture

We re-constructed and improved the Component Regression Network proposed in this paper.
Generally, we regressed the residual image between the beautified one and the original one in the scaled-component space.

Result

Related work