Cool work, thanks for sharing! I saw briefly in the video https://youtu.be/QlfCfkzkBB4?si=xkuPS0Dj9Z9hnjAP&t=57 that you were using 3d renderings of eyes for training? Did you find a rigged eye like that, or make it? So it worked well enough for training. Are you using actual captures for training too? or is it not worth using?

Thank you! John found UnityEyes2 (aleksmcfly) and trained off it alongside some data the main developer for this curated, but we want to use actual captures!

Our goal is to use 40 people to create around 1200 minutes of training footage we can use to make things more robust on some serious hardware! We are going to use around 5 headset models to do this alongside a varied enough demographic to account for ethnicities often ignored with these solutions (Chinese, Japanese, anyone with monolids really alongside pale and dark skin)

Good job, will try this

I have to give all thanks to John, the main dev pushing the eye tracking!

It is demoable currently within the Github and we hope to increase quality substantially with a few people willing to help us make a dataset!