AI RESEARCH
VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model
arXiv CS.CV
•
ArXi:2603.12655v1 Announce Type: new World models that forecast scene evolution by generating future video frames devote the bulk of their capacity to photometric details, yet the resulting predictions often remain geometrically inconsistent. We present VGGT-World, a geometry world model that side-steps video generation entirely and instead forecasts the temporal evolution of frozen geometry-foundation-model (GFM) features.