Name
BeautyMirror
Source
Paper: http://liusi-group.com/pdf/BeautyGAN-camera-ready_2.pdf
Pretrained Module: https://drive.google.com/drive/folders/1pgVqnF2-rnOxcUQ3SO4JwHUFTdiSe5t9
Presentation: https://docs.google.com/presentation/d/1DKCaDpAfye6AF4DmrT1d3hjaJCn3PrIQfMcUBAmh2-A/edit?usp=sharing
Inspirations
Nowadays, there are lots of beauty cams in the market that can beautify user’s portraits (transfer the style of makeups) and outputs a better-looking photo than the original one. However, users can either have limited options to select preset models or manually set some abstract configurations described by jargon. These configs indeed guarantee the quality of outcomes, and yet they limit the creativity. The face can be a very personal thing and should be customized based on users’ will.
So, here comes the BeautyMirror, a GAN network by Tsinghua University that extracts makeup features from a face in one image as a model and transfer the makeup style of the input image. The network will detect some feature points of faces, for example, the style of the nose, lip, eye shadow, etc.
The advantage of the project is that by utilizing the power of GAN, the users can change their face style to any portraits they upload which gives the users more freedom when experiencing the project. The challenges are also lying on the ground that I need to be cautious when selecting preset models(images) that have an impressive impact on users.
Demo
One Reply to “Week 12: Final Proposal – Jinzhong”