ASTRA is a plug-and-play training-free method for precise multi-subject video editing that uses prompt-guided multimodal alignment and prior-based mask retargeting to avoid attention dilution and boundary issues.
R-genie: Reasoning-guided gener- ative image editing.arXiv preprint arXiv:2505.17768
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Introduces ProductConsistency dataset, benchmark, and Cyclic Consistency reward to fine-tune image editing models, achieving a 5x reduction in character error rate for product identity preservation.
citing papers explorer
-
ASTRA: Let Arbitrary Subjects Transform in Video Editing
ASTRA is a plug-and-play training-free method for precise multi-subject video editing that uses prompt-guided multimodal alignment and prior-based mask retargeting to avoid attention dilution and boundary issues.
-
ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
Introduces ProductConsistency dataset, benchmark, and Cyclic Consistency reward to fine-tune image editing models, achieving a 5x reduction in character error rate for product identity preservation.