ProxiMAP enhances PnP restoration by using a noise schedule that keeps the denoiser in-distribution for reliable MAP approximation, yielding sharper images than standard MMSE or direct MAP targeting.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
citing papers explorer
-
Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
ProxiMAP enhances PnP restoration by using a noise schedule that keeps the denoiser in-distribution for reliable MAP approximation, yielding sharper images than standard MMSE or direct MAP targeting.
-
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.