SFBD Flow converts the iterative SFBD approach into a continuous optimization framework for diffusion models on noisy samples, with its Online SFBD instantiation outperforming baselines.
An expectation-maximization algorithm for training clean diffusion models from corrupted observations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples
SFBD Flow converts the iterative SFBD approach into a continuous optimization framework for diffusion models on noisy samples, with its Online SFBD instantiation outperforming baselines.