Interactive Media Arts @ NYUSH
My final project mainly simulates the movement of colors in water and provides an interactive model for users to experience color diffusion, where they can also create some appealing visuals. Inspired by marbling, I used GUI to enable users to pick colors and adjust the viscosity of water. Along with some other choices, users can drag the mouse and explore the colors mobility.
As I developed my final project, I made some adjustment based on my original proposal. I used to plan to make a simple way for people to do daily logs in which they can spend less effort achieving pretty visual effects. But later I decided to narrow the concept to target a more specific group of people who want to record the places they have been. Thus, TrackLog Generator can be a useful tool for them to create some artful and unique visuals for their tracks. As for the machine learning part, I mainly used Style Transfer and CycleGAN and trained them separately.
For this week’s assignment, we are supposed to spend some time on CycleGAN. At first, I accidentally retrained monet2photo, so I just explored more about this model by doing some inferences.
Here are some of my results:
From my observation, the model works much better on the paintings of scenery than those of people. For the paintings of people, they are more like added a blur filter without too many changes. However, even though the results of scenery paintings are not too bad, it is still not realistic enough in my opinion, considering there are still some strokes in the picture.
And here is an example demonstration of monet2photo model I found online. Apparently, the effect is better than my results. I think it may be due to the different parameters during training, but I’m not sure which parameters would influence most.
Furthermore, I used some paintings of Van Gogh as the input to see their results under monet2photo model. I think the results are worse here than the portray paintings of Monet, but meanwhile there is still some similarity of the style for the outputs.
Besides, I trained CycleGAN using facades dataset, but the training process takes time and I may add more details about it later. 🙂
My link to Assignment 10.
This week, we are asked to do exploration about autonomous agents. What I made is a game similar to Snake where the user can manipulate the snake by mouse. When it touches fruits, the length of it will increase, but when it touches the obstacles in another color, the length of it will decrease. There is recording of its length on the left top corner, and when it reaches 30 or is less than 2, the game will end. The only thing that is different form the typical game is that the snake is composed of several circles which are all autonomous agents. They follow each other one by one so that the snake is more flexible and interesting. Of course, the current version of the game is not too difficult because I didn’t make the boundaries the obstacle as well. I think there can be more elements to add to the game to make it more challenging.
Here is my short video demo and the endpoint of the game in the video was set to 10:
As for final project, I want to make a simple way for people to do daily logs. Nowadays many people love to do bullet journal and then post them on media platform. However, it tends to be time-consuming when we try to make it as pretty as possible, which can be the majority reason why we cannot insist for a long time, especially for students or office works. Thus, I would like to create a way that people can do daily logs to record their highlight moments with pretty visuals but at the same time don’t need to spend too much time.
Continue reading “IML | Week11 Final Concept Proposal – Quoey Wu”