Discontinuity-Preserving Image Super-Resolution using MRF-Based MAP-Optimized One-Step Diffusion

TMLR Paper7180 Authors

Abstract: We propose a real-world image super-resolution framework that leverages a pretrained text-to-image Stable Diffusion model optimized for single-step sampling. Unlike traditional multi-step diffusion-based methods, which are computationally intensive, our approach enables fast inference while preserving high perceptual quality. To this end, we integrate a lightweight image enhancement module trained jointly with the diffusion model under a Maximum A Posteriori (MAP) formulation. The optimization includes a compound Markov Random Field (MRF) prior, derived from the anticipated discontinuity line field energy, which functions as a structural regularizer to preserve fine image details and facilitate deblurring. Existing single-step diffusion approaches often rely on distillation or noise map estimation, which limits their ability to generate rich pixel-space details. In contrast, our method explicitly models high-frequency line field consistency between the low- and high-resolution domains, guiding the image enhancer to reconstruct sharp outputs. By preserving and enhancing structural features such as edges and textures, our framework effectively handles complex degradations commonly encountered in real-world scenarios. Experimental results demonstrate that our method achieves performance that is comparable to or exceeds that of state-of-the-art single-step and multi-step diffusion-based image super-resolution methods qualitatively, quantitatively, and computationally.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Mauricio_Delbracio1

Submission Number: 7180