IFCSR：面向单步扩散真实世界图像超分辨率的免推理保真度-真实感控制
IFCSR: Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-Resolution
把保真度-真实感的可调控制从潜空间搬到图像空间，使一次推理后即可无额外推理地连续调节权衡，可直接复用于其他单步扩散复原任务（去噪、去模糊）的可控性设计。
原文依据 adjusts the fidelity-realism trade-off in the image space, rather than in the latent space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散模型近期在真实世界图像超分辨率（ISR）中取得了显著成功，通常需要在保真度（即与高分辨率图像的相似性）与真实感（即感知自然度）之间取得平衡。为更好地兼顾图像质量中的主观偏好，已有研究探索了基于扩散模型的可控方法，通过可调参数实现对该权衡的个性化调整。尽管现有可控方法已展现出有效的控制能力，但它们通常在潜空间中操作，并在调整过程中需要反复进行网络推理，最终限制了其实用性。本文提出 IFCSR，一种简单而实用的单步扩散真实世界 ISR 方法，可实现保真度与真实感之间的免推理控制。其核心思想是设计一个在图像空间而非潜空间中调整保真度-真实感权衡的可控模型。这种图像空间控制使用户在初次推理得到分别偏向保真度与真实感的图像之后，无需额外推理即可无缝调整该权衡。我们进一步引入两阶段训练方案与专门设计的损失函数，促使可控空间覆盖广泛的保真度与真实感范围。本方法在质量上与最优模型相当，同时通过免推理控制提供了实用优势。
英文原文摘要 1416 字符
Diffusion models have recently achieved remarkable success in real-world image super-resolution (ISR), typically balancing a trade-off between fidelity (i.e., similarity to HR images) and realism (i.e., perceptual naturalness). To better account for subjective preferences in image quality, controllable diffusion-based methods have been explored, allowing personalized adjustment of this trade-off via tunable parameters. While existing controllable methods have shown effective control, they typically operate in the latent space and require repeated network inference during adjustment, eventually limiting their practicality. In this paper, we propose IFCSR, a simple yet practical approach for one-step diffusion-based real-world ISR that enables inference-free control between fidelity and realism. The key idea is to design a controllable model that adjusts the fidelity-realism trade-off in the image space, rather than in the latent space. Such an image-space control allows users to seamlessly adjust the trade-off without extra inference after an initial inference of fidelity- and realism-specific images. We further introduce a two-stage training scheme and specialized losses that encourage the controllable space to span a broad spectrum of fidelity and realism. Our method achieves quality competitive with state-of-the-art models while providing a practical advantage through inference-free control.