Haoming Cai
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotemporal consistency during complex movements and occlusions.
Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotemporal consistency during complex movements and occlusions.
Papers
Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion
Jiayi Wu, Haoming Cai, Cornelia Fermuller, Christopher Metzler +1 more
Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotempora…