Perform texture-based (standard) and geometry-aware (novel) neural style transfer on human face images.

Images from left to right are: input content image (Audrey Hepburn in 1956, Public Domain), input style image (Girl with A Black Cat, by Henri Matisse 1910, Public Domain), a standard style transfer output, proposed method output (generated by the Author)

In this blog, I will talk about how to perform texture-based (standard) and geometry-aware (novel) neural style transfer on human face images based on the implementation of DST [1] and the Face of Art [2].

DST is a one-shot, optimization-based method for geometry-aware style transfer. Combining DST with the Face of Art’s style images and facial landmarks, we will unfold how this method can generate a better representation of the artist style compared to standard style transfer methods.

🌟 Want to play with it yourself? Check out my github repo for the demo and more visual results.


Most of the…

Morphing Jennie from Blackpink to Rihanna

Morphing isn’t an unfamiliar technique for the audience — it played a large role in pop culture in cinemas throughout the 90s, made famous by Michael Jackson’s 1991 video for “Black or White”. The video features faces of different ethnicity and gender jamming to the song and morphing into each other, as a great reminder that we are all more alike than different.

This technique of morphing between two clips together was extended from morphing two still images, which is surprisingly not very hard to implement. In this article, I will walk through the face morphing procedures step by step…


Recent advances in Generative Adversarial Network (GAN) have shown impressive results in the quality and resolution of the images synthesized, especially in the field of style transfer. Motivated by the recent success of StyleGAN [1], where stochastic variation is incorporated in the realistic-looking synthesized images, we propose to focus on one of the most practical variations — hairstyle.

A hairstyle, as an important part of personal appearance, can be expressive of one’s personality and overall style. More often than not, the right hairstyle can only be discovered through trial and error. …

Hi, It’s Azmarie,

a Business/Computing Science student at Simon Fraser University. I just finished my incredible 4-month co-op with ACL as a Software Engineer in the team Titanium. I had a great time there learning and growing beyond my expectations. With all the interesting challenges, team collaboration, and career development opportunities that I have been given, I am confident to say, I left as a more skilled, humbled, and well-rounded developer.

Being a foodie and a self-claimed good cook myself, I love a three-course meal where the appetizer gets you excited, the entree is steamy and filling, and the dessert…

I’m a Software Engineer, ☕️ and 🐱 lover. Previously, I was a graduate researcher in Computer Vision. Find me @

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store