A co-trained adapter framework enables mask-free local editing in DiTs by factorizing edit semantics from spatial location and jointly learning a mask predictor.
et al.\ (2026)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ControlLight introduces a controllable low-light enhancement model trained on a new large-scale real-world dataset using a misalignment-aware weighted flow matching loss for structural consistency across enhancement levels.
citing papers explorer
-
Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing
A co-trained adapter framework enables mask-free local editing in DiTs by factorizing edit semantics from spatial location and jointly learning a mask predictor.
-
ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement
ControlLight introduces a controllable low-light enhancement model trained on a new large-scale real-world dataset using a misalignment-aware weighted flow matching loss for structural consistency across enhancement levels.