Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling
This addresses the problem of efficient image acquisition for applications like medical imaging, though it appears incremental as it builds on existing diffusion models and adaptive CS concepts.
The paper tackles the problem of adaptive compressed sensing for image acquisition by proposing AdaSense, which uses zero-shot posterior sampling with pre-trained diffusion models to dynamically select measurements without additional training. The result is effective reconstruction of facial images from few measurements and potential acceleration in medical imaging domains like MRI and CT.
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.