Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation

De Vita M, Belagiannis V (2025)

Publication Type: Conference contribution

Publication year: 2025

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 3844-3854

Conference Proceedings Title: Proceedings - 2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025

Event location: Tucson, AZ US

ISBN: 9798331510831

DOI: 10.1109/WACV61041.2025.00378

Abstract

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 uncertainty during the sampling phase of diffusion models and utilise the uncertainty to improve the sample generation quality. The uncertainty is computed as the variance of the denoising scores with a perturbation scheme that is specifically designed for diffusion models. We then show that the aleatoric uncertainty estimates are related to the second-order derivative of the diffusion noise distribution. We evaluate our uncertainty estimation algorithm and the uncertainty-guided sampling on the ImageNet and CIFAR-10 datasets. In our comparisons with the related work, we demonstrate promising results in filtering out low quality samples. Furthermore, we show that our guided approach leads to better sample generation in terms of FID scores.

Authors with CRIS profile

Michele De Vita Professur für Maschinelles Lernen in der Signalverarbeitung Vasileios Belagiannis Professur für Maschinelles Lernen in der Signalverarbeitung

How to cite

APA:

De Vita, M., & Belagiannis, V. (2025). Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation. In Proceedings - 2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025 (pp. 3844-3854). Tucson, AZ, US: Institute of Electrical and Electronics Engineers Inc..

MLA:

De Vita, Michele, and Vasileios Belagiannis. "Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation." Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025, Tucson, AZ Institute of Electrical and Electronics Engineers Inc., 2025. 3844-3854.

BibTeX: Download