pointerpointer.com's use of voronoi, canvas, and javascript

Here's a picture of all the different regions: [LINK] For those curious if how it works, Paul Irish did a breakdown of it quite a while ago: [VIDEO] TL:DW - Vornoi Diagrams[1] and manual tagging, no machine learning needed. [1] [LINK]

I made a quick video explaining how the webapp works: [VIDEO] Essentially, using the gridPositions.json to populate a Voronoi Grid (toggle display of the <canvas> in your browser). Then your cursor position is used against the grid to find which shape encloses it which maps back to the source JPEG which is then displayed.

Paul Irish explained the basics of how it works here: [VIDEO] I wonder if you could create something similar nowadays using generative AI but with the finger in a very specific location without pregenerating thousands of images.