CVPR2024
PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor
Vidit Goel, Elia Peruzzo, Yifan Jiang, Dejia Xu, Xingqian Xu, Nicu Sebe, Trevor Darrell, Zhangyang Wang, Humphrey Shi
摘要
Contributions • General framework to enable precise object-level editing in Diffusion Models. • Comprehensive editing capabilities under a single model trained once. • Multimodal Classifier-free Guidance to control all editing operations using both text and images