Modeling quantization noise in compressed diffusion models as a time-step-dependent joint Gaussian, then correcting its mean and variance during sampling, improves FID over prior PTQ methods and can beat the full-precision model.
bioRxiv, 2022–07
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
Modeling quantization noise in compressed diffusion models as a time-step-dependent joint Gaussian, then correcting its mean and variance during sampling, improves FID over prior PTQ methods and can beat the full-precision model.