Diffusion-based inverse problem solvers are made robust to outliers by combining explicit noise estimation with a Huber-loss IRLS objective solved via conjugate gradient.
LatentPaint: Image inpainting in latent space with diffusion models
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
-
Outlier-Robust Diffusion Solvers for Inverse Problems
Diffusion-based inverse problem solvers are made robust to outliers by combining explicit noise estimation with a Huber-loss IRLS objective solved via conjugate gradient.