重新审视基于空间-语义引导的超分辨率中的感知-失真权衡
Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution
AI总结：
本文提出SpaSemSR框架，通过空间-语义引导减少失真并提升感知质量，实验显示在多个基准上实现了更优的感知-失真平衡。
摘要：
图像超分辨率（SR）旨在通过高感知质量和低失真重建高质量图像，但本质上受限于感知-失真权衡。基于GAN的SR方法减少失真但仍难以生成逼真细粒度纹理，而基于扩散模型的方法能够合成丰富的细节但往往偏离输入，产生幻觉结构并降低保真度。这种矛盾提出了一个关键挑战：如何利用扩散模型强大的生成先验而不牺牲保真度。为此，我们提出SpaSemSR，一种结合空间-语义引导的扩散框架，包含两种互补的引导机制。首先，空间引导文本引导将对象级空间线索与语义提示结合，对齐文本和视觉结构以减少失真。其次，语义增强的视觉引导通过多编码器设计和语义退化约束统一多模态语义先验，提升在严重退化下的感知真实性。这些互补的引导通过空间-语义注意力机制适配融合到扩散过程中，抑制失真和幻觉的同时保留扩散模型的优势。在多个基准上的广泛实验表明，SpaSemSR实现了更优的感知-失真平衡，生成既逼真又忠实的修复结果。
英文摘要：
Image super-resolution (SR) aims to reconstruct high resolution images with both high perceptual quality and low distortion, but is fundamentally limited by the perception-distortion trade-off. GAN-based SR methods reduce distortion but still struggle with realistic fine-grained textures, whereas diffusion-based approaches synthesize rich details but often deviate from the input, hallucinating structures and degrading fidelity. This tension raises a key challenge: how to exploit the powerful generative priors of diffusion models without sacrificing fidelity. To address this, we propose SpaSemSR, a spatial-semantic guided diffusion framework with two complementary guidances. First, spatial-grounded textual guidance integrates object-level spatial cues with semantic prompts, aligning textual and visual structures to reduce distortion. Second, semantic-enhanced visual guidance with a multi-encoder design and semantic degradation constraints unifies multimodal semantic priors, improving perceptual realism under severe degradations. These complementary guidances are adaptively fused into the diffusion process via spatial-semantic attention, suppressing distortion and hallucination while retaining the strengths of diffusion models. Extensive experiments on multiple benchmarks show that SpaSemSR achieves a superior perception-distortion balance, producing both realistic and faithful restorations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
