Interactive Media Arts @ NYUSH
Style Filter is an interactive installation powered by Arduino, p5.js and ml5.js. It incorporates a physical interface for users to apply neural style transfer filters to images, in a way that one would apply a square filter on a camera lens into a holder. As multiple filter holders are provided, users are free to explore applying filters on top of each other in various orders.
Continue reading “IML | Style Filter: Final Project Documentation – Yufeng”
For this week, I am training a CycleGAN model which transfers photographs to the style of Todd Hido, one of my favorite photographers.
For real life photographs, I used the Domain B from the ukiyoe2photo dataset. There are around 6300 images, which I probably should have trimmed down for faster training since the number is significantly larger than Domain B.
The works of Hido has a mysterious and atmospheric vibe. I collected 400 photographs of him from a photographer community, including landscapes and portraits.
I am (still) training the model on my workstation with a GTX 1080. The estimated time of 100 epochs is 50 hours, so it should be done by the end of May 7th.
Here are some samples generated while training at epoch 20. There is clearly some fogs added into the transfer real photo.
Style transfer selfies to the style of an existing self-portrait piece which has the most similar facial expression.
Continue reading “IML | Week 11: Final Project Proposal – Yufeng”
For this week’s deep dream experiment, I used photos that I took as input image. The goal is to blend in deep dream visuals as a part of the original photo. Since it is not possible to specify which area to “deep dream” in the code, I mask part of the image out with Photoshop.
As I’ve trained several models for the midterm, I only trained one this week. I did it on my own desktop with a GTX 1080 on Ubuntu for two epochs. Some artifacts are quite visible probably because the lack of epochs in training.
The style is based on a Blade Runner style poster I found on Pinterest.
In the following inferencing, I also used another one of models which I trained in the weeks before.
The other style is Convergence, 1952 by Pollock.
I reused the code from my midterm project to perform a multilayer style transfer. I decided to experiment on transferring to two styles back and forth.
The source image being transferred
The fusion of two styles works is quite effective but converges a stable effect with small “chunky” style transfer artifacts.