Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion 文章

ArXiv CS.CV2026-06-02NEWSen作者: Jiayi Wu, Haoming Cai, Cornelia Fermuller, Christopher Metzler, Yiannis Aloimonos
查看原文 →
关系图谱

Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion · 相关技术

相关技术

3D lifting modelslatent video diffusion models