[Paper-Reading]
VGGT-Long: hunk it, Loop it, Align it – Pushing VGGT’s Limits on Kilometer-scale Long RGB Sequences
Kai Deng, Zexin Ti, Jiawei Xu, Jian Yang, Jin Xie
arxiv.org/pdf/2507.16443
Major idea:
1. VGGT on chunk of images
2. Visual place recognition
3. Global pose graph
