以可控单步扩散弥合保真度与真实感：面向图像超分辨率
Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
可复用的思路有两点：一是用未压缩的 LQ 原始信息做特征调制，为扩散过程提供高保真条件，缓解压缩编码带来的信息损失；二是区域自适应地激活生成先验，并用文本匹配引导对齐语义区域，在单步推理下兼顾感知质量与局部结构保真。
原文依据 we propose CODSR, a controllable one-step diffusion network for image super-resolution
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期基于扩散模型的单步方法在图像超分辨率领域取得了显著进展，但仍受三方面关键限制的制约：（1）低质量（LQ）输入的压缩编码造成信息损失，导致保真度表现较差；（2）生成先验的区域判别性激活不足；（3）文本提示与其对应语义区域之间存在错位。为解决上述限制，我们提出 CODSR，一种用于图像超分辨率的可控单步扩散网络。首先，我们提出 LQ 引导的特征调制模块，利用 LQ 输入中未经压缩的原始信息，为扩散过程提供高保真的条件。随后，我们开发了一种区域自适应的生成先验激活方法，在不牺牲局部结构保真度的前提下有效增强感知丰富度。最后，我们采用文本匹配引导策略，以充分发挥文本提示的条件潜力。大量实验表明，CODSR 在保持高效单步推理的同时，相较最优方法取得了更优的感知质量与有竞争力的保真度。
英文原文摘要 1211 字符
Recent diffusion-based one-step methods have shown remarkable progress in the field of image super-resolution, yet they remain constrained by three critical limitations: (1) inferior fidelity performance caused by the information loss from compression encoding of low-quality (LQ) inputs; (2) insufficient region-discriminative activation of generative priors; (3) misalignment between text prompts and their corresponding semantic regions. To address these limitations, we propose CODSR, a controllable one-step diffusion network for image super-resolution. First, we propose an LQ-guided feature modulation module that leverages original uncompressed information from LQ inputs to provide high-fidelity conditioning for the diffusion process. We then develop a region-adaptive generative prior activation method to effectively enhance perceptual richness without sacrificing local structural fidelity. Finally, we employ a text-matching guidance strategy to fully harness the conditioning potential of text prompts. Extensive experiments demonstrate that CODSR achieves superior perceptual quality and competitive fidelity compared with state-of-the-art methods while maintaining efficient one-step inference.