Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Haoming Cai

Haoming Cai

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Vision×2AI×2

Frequent co-authors

Jiayi Wu2×
Cornelia Fermuller2×
Christopher Metzler2×
Yiannis Aloimonos2×

Research Timeline

2026
Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion

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: Generative 3D Caches as Complementary Context for Video Diffusion

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.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentMay 29, 2026

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…

View →
cs.CVcs.AIRecentMay 29, 2026

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…

View →