Multi-scale Conditional Generative Modeling for Microscopic Image Restoration

TL;DR

This paper introduces a multi-scale conditional generative model using a Brownian Bridge process in the wavelet domain to improve microscopic image restoration, achieving faster training and sampling with high-quality results.

Contribution

It presents a novel multi-scale diffusion model leveraging the Brownian Bridge process in the wavelet domain for efficient microscopic image restoration.

Findings

Significant acceleration in training and sampling times.

High-quality image restoration comparable to state-of-the-art methods.

Robust performance across various microscopy tasks.

Abstract

The advance of diffusion-based generative models in recent years has revolutionized state-of-the-art (SOTA) techniques in a wide variety of image analysis and synthesis tasks, whereas their adaptation on image restoration, particularly within computational microscopy remains theoretically and empirically underexplored. In this research, we introduce a multi-scale generative model that enhances conditional image restoration through a novel exploitation of the Brownian Bridge process within wavelet domain. By initiating the Brownian Bridge diffusion process specifically at the lowest-frequency subband and applying generative adversarial networks at subsequent multi-scale high-frequency subbands in the wavelet domain, our method provides significant acceleration during training and sampling while sustaining a high image generation quality and diversity on par with SOTA diffusion models. Experimental results on various computational microscopy and imaging tasks confirm our method's robust performance and its considerable reduction in its sampling steps and time. This pioneering technique offers an efficient image restoration framework that harmonizes efficiency with quality, signifying a major stride in incorporating cutting-edge generative models into computational microscopy workflows.