Preprint
Oct 2026
GAD: Geometry Attention Distillation for Consistent Video Generation
Video diffusion models generate visually compelling short-term sequences but often struggle to preserve scene geometry and object structure over time. In this paper, we first demonstrate that current video attention cannot identify reliable correspondences across frames, with responses dispersed across multiple regions...
Jun-Feng Ni, Zi-Yu Zhu, Fan Jiang et al.
· 0 citations