A training-free method with time-dependent attention gating and trajectory pruning enhances object-background balance in diffusion-based image synthesis.
IEEE Transactions on Neural Networks and Learn- ing Systems27(6), 1214–1226 (2015)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
A training-free method with time-dependent attention gating and trajectory pruning enhances object-background balance in diffusion-based image synthesis.