AI Dynamics

Global AI News Aggregator

About

Single Vanilla Transformer Outperforms All SOTA 3D Models

Holy shit… a single vanilla transformer is outperforming every SOTA 3D model. Depth Anything 3 just rewired 3D perception. A single plain transformer no fancy architecture now reconstructs full 3D geometry from any set of images. One photo, 18 photos, posed or unposed, it

→ View original post on X — @godofprompt