How do we teach AI to see the world in 360°?

A new survey dives deep into panoramic vision — exploring how models adapt from standard perspective images to omnidirectional images (ODIs) used in VR, robotics, and autonomous driving.

The paper reviews 300+ works and identifies… pic.twitter.com/tgmWmnRwJI

— 机器之心 JIQIZHIXIN (@jiqizhixin) 8 octobre 2025

How do we teach AI to see the world in 360°? A new survey dives deep into panoramic vision — exploring how models adapt from standard perspective images to omnidirectional images (ODIs) used in VR, robotics, and autonomous driving. The paper reviews 300+ works and identifies

→ View original post on X — @jiqizhixin,