Empirical study finds synthetic-to-real domain gap sharply degrades diffusion SR models on real cross-sensor satellite pairs while real-data training faces optimization and adaptation problems.
Unidb: A uni- fied diffusion bridge framework via stochastic optimal control.arXiv preprint arXiv:2502.05749
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5verdicts
UNVERDICTED 5representative citing papers
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
A trajectory optimal control framework for reward-guided image editing in diffusion models that balances reward maximization with source fidelity better than prior inversion-based baselines.
SOCS derives per-step closed-form control signals from stochastic optimal control to steer diffusion sampling trajectories toward measurements while preserving the generative prior.
Stochastic image enhancement methods are shown to be variants of a shared SDE differing in drift, diffusion, terminal distributions and boundary conditions, with controlled experiments revealing no single dominant family and a new modular library released.
citing papers explorer
-
Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
A trajectory optimal control framework for reward-guided image editing in diffusion models that balances reward maximization with source fidelity better than prior inversion-based baselines.