Wow so much exciting progress on Structure-from-Motion this week! Congratulations to Jianyuan Wang Jerome Revaud Eric Brachmann Vincent Sitzmann & teams for their fantastic works! Now we really feel pressured to improve COLMAP before everyone catches up 😉

What a stunning view for International Conference on 3D Vision in Davos! It’s been very fun meeting so many people doing great work in the space of 3D vision 😀

For #NeurIPS2023 we're presenting our latest work SNAP - Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding
Geo data at scale + self-supervision = 💥
Video: youtu.be/xogrwdgNQdo
Paper: arxiv.org/pdf/2306.05407
Code: github.com/google-researc…
summary🧵⬇️

AK #gs

Very cool work by Frank Fu & Maurice Fallon extending Back to the Feature to Camera-Lidar calibration. Learned image-lidar representations + differentiable geometry optimization FTW!
As expected, great generalization compared to black-box deep nets.

My TED talk is live at ted.com/talks/sasha_lu…!
Check it out for memes 🖼️, emissions 🌎 and hot takes 🌶️
The TLDR? Focusing on the future existential risks of AI is a distraction from its current impacts and mitigating them.

'We must take the risks of AI as seriously as climate change. We can’t afford the same delay with AI.'

This planet will be hell long before AI becomes smart enough to be an existential risk: ~30% of the population lives in areas unliveable by 2070. AI risk is a mere distraction.