Perceptually Regularized Diffusion Model for Image Super-Resolution

2026-09-01

AI Summary

本文针对图像超分辨率问题，提出了一种结合感知损失正则化的扩散模型方法，以改善高分辨率图像重建的质量和结构细节。

Abstract

Image super-resolution, which aims to reconstruct high-resolution images from their low-resolution observations, is fundamental to medical imaging, remote sensing, surveillance, microscopy, and scientific visualization. Traditional model-based methods formulate super-resolution as an inverse problem with hand-crafted regularization priors. While interpretable and theoretically grounded, they rely on fixed assumptions and require computationally intensive iterative solvers. Deep learning methods offer data-driven flexibility by learning nonlinear mappings from low- to high-resolution images, among which diffusion models have achieved particularly impressive perceptual quality. However, the standard diffusion training objective is a pixel-domain noise-prediction loss that does not explicitly enforce perceptual fidelity, which can lead to oversmoothing and loss of fine image structure. To address these limitations, we propose a perceptually regularized diffusion framework that incorporates prior knowledge through perceptual-loss-based regularization, improving training convergence and encouraging the recovery of meaningful image features. Experiments on benchmark datasets demonstrate improved perceptual quality and competitive distortion metrics, highlighting the effectiveness of regularization for diffusion-based super resolution.

Problem

• Image Super-Resolution
• Perceptual Fidelity
• Diffusion Models

Innovation

• perceptual regularization
• diffusion model
• super-resolution
• perceptual loss