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.
A high-quality denoising dataset for smartphone cameras
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
-
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.