General Intelligent Imaging and Uncertainty Quantification by Deterministic Diffusion Model

TL;DR

This paper introduces a deterministic diffusion model (DDM) for efficient, scalable, and reliable computational imaging that handles complex nonlocal patterns and incorporates uncertainty quantification, outperforming previous deep learning methods.

Contribution

The paper presents a novel DDM framework that enables universal imaging with low computational cost and integrates Bayesian inference for uncertainty quantification.

Findings

Demonstrates superior image reconstruction from nonlocal patterns.

Shows effective uncertainty quantification in imaging tasks.

Outperforms previous state-of-the-art DL algorithms.

Abstract

Computational imaging is crucial in many disciplines from autonomous driving to life sciences. However, traditional model-driven and iterative methods consume large computational power and lack scalability for imaging. Deep learning (DL) is effective in processing local-to-local patterns, but it struggles with handling universal global-to-local (nonlocal) patterns under current frameworks. To bridge this gap, we propose a novel DL framework that employs a progressive denoising strategy, named the deterministic diffusion model (DDM), to facilitate general computational imaging at a low cost. We experimentally demonstrate the efficient and faithful image reconstruction capabilities of DDM from nonlocal patterns, such as speckles from multimode fiber and intensity patterns of second harmonic generation, surpassing the capability of previous state-of-the-art DL algorithms. By embedding Bayesian inference into DDM, we establish a theoretical framework and provide experimental proof of its uncertainty quantification. This advancement ensures the predictive reliability of DDM, avoiding misjudgment in high-stakes scenarios. This versatile and integrable DDM framework can readily extend and improve the efficacy of existing DL-based imaging applications.