发表机构
University of North Carolina; Texas Tech University; Case Western Reserve University; University of Houston; University of Kentucky（北卡罗来纳大学; 德克萨斯理工大学; 凯斯西储大学; 休斯顿大学; 肯塔基大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对扩散模型图像超分辨率的像素域噪声预测损失易致过平滑的问题，提出感知正则化扩散框架，实验证实其可提升感知质量与失真度量表现。
AI 中文摘要
图像超分辨率旨在从低分辨率观测中重建高分辨率图像，是医学成像、遥感、监控、显微镜检查及科学可视化的基础。传统基于模型的方法将超分辨率表述为带有手工设计正则化先验的逆问题，虽具可解释性和理论基础，但依赖固定假设且需计算密集型迭代求解器。深度学习方法通过学习从低分辨率到高分辨率图像的非线性映射提供数据驱动的灵活性，其中扩散模型已实现令人印象深刻的感知质量。然而，标准扩散训练目标是像素域噪声预测损失，未明确强制感知保真度，可能导致过度平滑和精细图像结构丢失。为解决这些局限，我们提出感知正则化扩散框架，通过基于感知损失的正则化融入先验知识，提升训练收敛性并鼓励恢复有意义的图像特征。在基准数据集上的实验表明，该方法改善了感知质量并具备有竞争力的失真度量，凸显了正则化对基于扩散的超分辨率的有效性。
英文摘要
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.
