English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Diffusion models have impressive image generation capability, but low-qualitygenerations still exist, and their identification remains challenging due tothe lack of a proper sample-wise metric. To address this, we propose BayesDiff,a pixel-wise uncertainty estimator for generations from diffusion models basedon Bayesian inference. In particular, we derive a novel uncertainty iterationprinciple to characterize the uncertainty dynamics in diffusion, and leveragethe last-layer Laplace approximation for efficient Bayesian inference. Theestimated pixel-wise uncertainty can not only be aggregated into a sample-wisemetric to filter out low-fidelity images but also aids in augmenting successfulgenerations and rectifying artifacts in failed generations in text-to-imagetasks. Extensive experiments demonstrate the efficacy of BayesDiff and itspromise for practical applications.

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference