ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction

TL;DR

ADOBI introduces an adaptive diffusion bridge framework that calibrates unknown forward models to enforce measurement consistency, enabling fast and high-quality MRI reconstruction in blind inverse problems.

Contribution

This paper presents ADOBI, a novel adaptive diffusion bridge method that maintains measurement consistency in blind inverse problems, significantly improving MRI reconstruction speed and quality.

Findings

Achieves high-quality MRI reconstruction in 5-10 steps.

Outperforms existing methods on perception-distortion trade-off.

Consistently delivers state-of-the-art performance.

Abstract

Diffusion bridges (DB) have emerged as a promising alternative to diffusion models for imaging inverse problems, achieving faster sampling by directly bridging low- and high-quality image distributions. While incorporating measurement consistency has been shown to improve performance, existing DB methods fail to maintain this consistency in blind inverse problems, where the forward model is unknown. To address this limitation, we introduce ADOBI (Adaptive Diffusion Bridge for Inverse Problems), a novel framework that adaptively calibrates the unknown forward model to enforce measurement consistency throughout sampling iterations. Our adaptation strategy allows ADOBI to achieve high-quality parallel magnetic resonance imaging (PMRI) reconstruction in only 5-10 steps. Our numerical results show that ADOBI consistently delivers state-of-the-art performance, and further advances the Pareto frontier for the perception-distortion trade-off.