Quantitative flow matching adapts denoising by estimating noise from pixel statistics and tuning the inference trajectory accordingly for better accuracy and efficiency across noise levels.
Scaling rectified flow transformers for high-resolution image synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising
Quantitative flow matching adapts denoising by estimating noise from pixel statistics and tuning the inference trajectory accordingly for better accuracy and efficiency across noise levels.