A new decoupled diffusion guidance method enables efficient zero-shot inpainting by avoiding backpropagation through the denoiser while maintaining observation consistency and quality.
Will Grathwohl, Ricky T
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2representative citing papers
FMPlug adapts foundation flow-matching models into practical priors for inverse problems by combining instance-guided warm-start with sharp Gaussianity regularization, showing superior results on image restoration and scientific tasks with limited samples.
citing papers explorer
-
Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance
A new decoupled diffusion guidance method enables efficient zero-shot inpainting by avoiding backpropagation through the denoiser while maintaining observation consistency and quality.
-
Saving Foundation Flow-Matching Priors for Inverse Problems
FMPlug adapts foundation flow-matching models into practical priors for inverse problems by combining instance-guided warm-start with sharp Gaussianity regularization, showing superior results on image restoration and scientific tasks with limited samples.