Just a short post to host the slides and code from my Bristech talk “How to Capture the World, or Making Computers See in 3D”. It’s a short talk around computer vision, specifically a high level how-to on capturing 3D models from photos.
This post is up in advance of my talk, so spoilers in the slides and code if you’ve not seen it yet.
Making underwater robots see in 3D is part of what I do at Rovco. If it’s an interesting topic, even though your skills might be in other areas – we’re hiring in my team.
if you’re interested in my podcast, Pincount, I can recommend the “What is AI?” episode as an accessible place to start.