DriftSR：通过分布漂移实现一步式真实世界图像超分辨率

中文摘要 AI 辅助

一步式真实世界图像超分辨率（Real-ISR）提供了高效的推理，但恢复逼真且感知上丰富的细节通常依赖于分数蒸馏或对抗性学习，这引入了额外的可训练组件并使优化更加繁琐。为此，我们提出了DriftSR，一种通过分布漂移利用预训练扩散先验的一步式Real-ISR框架。具体来说，我们在预训练扩散模型的冻结中间表示空间中进行漂移，而无需引入额外的任务特定特征编码器。基于该空间，我们引入了空间特征漂移，将空间特征而非整个图像视为分布样本，从而为分布对齐提供更密集的监督。为了减轻结构偏差，我们进一步引入了结构调制引导，该引导根据与低质量（LQ）输入的局部结构一致性自适应地细化漂移引导。因此，DriftSR仅优化一步式生成器，无需辅助蒸馏分支或对抗性判别器。在三个真实世界基准上的广泛实验表明，DriftSR能够以高效的一步式推理提供高质量的超分辨率重建。

英文摘要

One-step real-world image super-resolution (Real-ISR) offers efficient inference, but recovering realistic and perceptually rich details often relies on score distillation or adversarial learning, introducing additional trainable components and making optimization more cumbersome. To this end, we propose DriftSR, a one-step Real-ISR framework that leverages pretrained diffusion priors through distribution drifting. Specifically, we perform drifting in the frozen intermediate representation space of a pretrained diffusion model, without introducing an additional task-specific feature encoder. Building on this space, we introduce Spatial Feature Drifting, which treats spatial features rather than entire images as distributional samples, enabling denser supervision for distribution alignment. To mitigate structural deviations, we further introduce Structure-Modulated Guidance, which adaptively refines drifting guidance according to local structural consistency with the LQ input. Consequently, DriftSR optimizes only the one-step generator, without auxiliary distillation branches or adversarial discriminators. Extensive experiments on three real-world benchmarks demonstrate that DriftSR delivers high-quality super-resolution reconstruction with efficient one-step inference.

发表机构

• Nanjing University of Science and Technology（南京理工大学）
• Huawei（华为）
• Nanjing University（南京大学）
• South China University of Technology（华南理工大学）

机构由 AI 辅助整理，请以论文原文为准。