AI RESEARCH
VGGT-$\Omega$
arXiv CS.CV
•
ArXi:2605.15195v1 Announce Type: new Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks. Here, we show that the quality of these models scales predictably with model and data size. We do so by