Measurement-Guided Consistency Model Sampling for Inverse Problems
This work addresses the practical deployment bottleneck for inverse problem reconstruction in imaging, though it is incremental as it builds on existing consistency models.
The paper tackled the slow sampling of diffusion models for inverse imaging problems by adapting consistency models to enforce measurement fidelity, achieving improved perceptual and pixel-level metrics on Fashion-MNIST and LSUN Bedroom datasets with only a few steps.
Diffusion models have become powerful generative priors for solving inverse imaging problems, but their reliance on slow multi-step sampling limits practical deployment. Consistency models address this bottleneck by enabling high-quality generation in a single or only a few steps, yet their direct adaptation to inverse problems is underexplored. In this paper, we present a modified consistency sampling approach tailored for inverse problem reconstruction: the sampler's stochasticity is guided by a measurement-consistency mechanism tied to the measurement operator, which enforces fidelity to the acquired measurements while retaining the efficiency of consistency-based generation. Experiments on Fashion-MNIST and LSUN Bedroom datasets demonstrate consistent improvements in perceptual and pixel-level metrics, including Fréchet Inception Distance, Kernel Inception Distance, peak signal-to-noise ratio, and structural similarity index measure, compared to baseline consistency sampling, yielding competitive or superior reconstructions with only a handful of steps.