BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
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.
Code (1)
Tasks
Bayesian InferenceImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation
Despite the remarkable progress in generative modelling, current diffusion models lack a quantitative approach to assess image quality. To address this limitation, we propose to estimate the pixel-wise aleatoric uncertai…
DenoisingShedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models
Generative diffusion models, notable for their large parameter count (exceeding 100 million) and operation within high-dimensional image spaces, pose significant challenges for traditional uncertainty estimation methods …
UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
Estimating the 6D pose of novel objects is a fundamental yet challenging problem in robotics, often relying on access to object CAD models. However, acquiring such models can be costly and impractical. Recent approaches …
6D Pose Estimation3D ReconstructionPatch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification
Diffusion models enable probabilistic super-resolution and conditional generation, but pixel-space methods are computationally expensive and learned latent spaces often lack interpretable uncertainty quantification. We i…
FaithFusion: Harmonizing Reconstruction and Generation via Pixel-wise Information Gain
In controllable driving-scene reconstruction and 3D scene generation, maintaining geometric fidelity while synthesizing visually plausible appearance under large viewpoint shifts is crucial. However, effective fusion of …
Scene Generation