AI RESEARCH
EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
arXiv CS.CV
•
ArXi:2602.15031v2 Announce Type: replace High-fidelity generative video editing has seen significant quality improvements by leveraging pre-trained video foundation models. However, their computational cost is a major bottleneck, as they are often designed to inefficiently process the full video context regardless of the inpainting mask's size, even for sparse, localized edits. In this paper, we