BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
Siqi Kou, Lei Gan, Dequan Wang, Chongxuan Li, Zhijie Deng
Abstract
Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper sample-wise metric. To address this, we propose BayesDiff, a pixel-wise uncertainty estimator for generations from diffusion models based on Bayesian inference. In particular, we derive a novel uncertainty iteration principle to characterize the uncertainty dynamics in diffusion, and leverage the last-layer Laplace approximation for efficient Bayesian inference. The estimated pixel-wise uncertainty can not only be aggregated into a sample-wise metric to filter out low-fidelity images but also aids in augmenting successful generations and rectifying artifacts in failed generations in text-to-image tasks. Extensive experiments demonstrate the efficacy of BayesDiff and its promise for practical applications.
BibTeX
@inproceedings{
kou2024bayesdiff,
title={BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference},
author={Siqi Kou and Lei Gan and Dequan Wang and Chongxuan Li and Zhijie Deng},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=YcM6ofShwY}
}