Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling

TL;DR

AdaSense introduces a zero-shot adaptive compressed sensing method using diffusion models to efficiently select measurements, enabling high-quality image reconstruction with minimal training across various domains.

Contribution

The paper presents AdaSense, a novel adaptive compressed sensing framework that employs diffusion-based posterior sampling, eliminating training needs and enabling versatile, domain-agnostic measurement selection.

Findings

Effective facial image reconstruction from few measurements

Successful application to MRI and CT image acquisition

Demonstrates potential for real-world imaging acceleration

Abstract

Compressed Sensing (CS) facilitates rapid image acquisition by selecting a small subset of measurements sufficient for high-fidelity reconstruction. Adaptive CS seeks to further enhance this process by dynamically choosing future measurements based on information gleaned from data that is already acquired. However, many existing frameworks are often tailored to specific tasks and require intricate training procedures. We propose AdaSense, a novel Adaptive CS approach that leverages zero-shot posterior sampling with pre-trained diffusion models. By sequentially sampling from the posterior distribution, we can quantify the uncertainty of each possible future linear measurement throughout the acquisition process. AdaSense eliminates the need for additional training and boasts seamless adaptation to diverse domains with minimal tuning requirements. Our experiments demonstrate the effectiveness of AdaSense in reconstructing facial images from a small number of measurements. Furthermore, we apply AdaSense for active acquisition of medical images in the domains of magnetic resonance imaging (MRI) and computed tomography (CT), highlighting its potential for tangible real-world acceleration.