paper-with-me

Papers

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

2023-10-17 · Siqi Kou, Lei Gan, Dequan Wang, Chongxuan Li, Zhijie Deng

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.

📄 PDF Abstract BibTeX arXiv:2310.11142

Code (1)

karrykkk/bayesdiff 공식 구현 pytorch

Tasks

Bayesian InferenceImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation

2024-11-29 · Michele De Vita, Vasileios Belagiannis

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…

Denoising

Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models

2024-06-05 · Lucas Berry, Axel Brando, David Meger

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

2025-08-21 · Zhaodong Jiang, Ashish Sinha, Tongtong Cao, Yuan Ren 외 arxiv

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 Reconstruction

Patch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification

2026-06-30 · Onkar Jadhav, Tim French, Matthew Rayson, Nicole L. Jones arxiv

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

2025-11-26 · YuAn Wang, Xiaofan Li, Chi Huang, Wenhao Zhang 외 arxiv

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