arXiv cs.AI
· Papers
GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling
arXiv:2606.20799v2 Announce Type: replace-cross Abstract: Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, causing entities that reappear across shots -- characters, objects, and locations -- to drift away from how they f