.png){kind=icon}
.png){kind=icon}
Return
Semantic-aware content alignment for multi-object video editing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.inffus.2026.104596.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a novel SemEdit for Zero-shot multi-object video editing. • A semantic adaptive modulation is designed to decouple entangled semantic distribution. • A semantic prior modeling is devised to ensure semantic alignment between video and prompt.
Keywords:
Diffusion model
Multi-object video editing
Semantic adaptive modulation
Semantic prior modeling
Journal
IF:
15.5
Papers:
4.1K
Citations:
2.7W
View more organizations