Inspiration
OptiFrame challenge track
What it does
It takes a photo of an eye glass lens, L and R, and combines them into a compelted 3d glasses frame model
How we built it
Mostly Python, OpenCV, and ArUco tags
Challenges we ran into
It was really hard ensuring photos at angles were aligned and the measurements were accurate. It's one thing to train an ML model on data but when it's in the real world there's a lot more problems you don't expect
Accomplishments that we're proud of
Getting accurate scale measurements of the lens, and generating a smooth, complete contour, and building a legitimate 3D model that can be 3d printed and used.
What's next for OptiFrame
Training models to detect the glasses instead of traditional CV techniques
Log in or sign up for Devpost to join the conversation.