面向可控真实世界图像超分辨率的单步扩散 Transformer
One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution
把 Qwen-Image 这类大规模扩散 Transformer 改造成单步 Real-ISR 的骨干，用双视觉流（可调噪声 + 一致噪声）在一步内同时保住保真度与提示词可控性，可直接迁移到其他单步复原/翻译式复原任务（去噪、去模糊、老照片修复）并复用其 FAA 训练策略。
原文依据 a newly introduced visual stream receives low-quality images (LQ) with adjustable noise (Control Noise)
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真实世界图像超分辨率（Real-ISR）进展已展现出显著的感知质量，但保真度与可控性之间的平衡仍是一个问题：多步扩散方法受生成多样性与随机性影响，导致保真度偏低；而单步方法因面向保真度的微调而丧失了控制灵活性。本文提出 ODTSR，一种基于 Qwen-Image 的单步扩散 Transformer，在同时兼顾保真度与可控性的前提下执行 Real-ISR：新引入的视觉流接收带可调噪声的低质量图像（LQ）（Control Noise），原始视觉流接收带一致噪声的 LQ（Prior Noise），从而构成噪声混合视觉流（NVS）设计。ODTSR 进一步采用保真度感知对抗训练（FAA）以增强可控性并实现单步推理。大量实验表明，ODTSR 不仅在通用 Real-ISR 上取得最优（SOTA）性能，还能在无需针对特定数据集训练的情况下，对中文真实场景文字图像超分辨率（STISR）等挑战性场景实现提示词可控。
英文原文摘要 1231 字符
Recent advances in diffusion-based real-world image super-resolution (Real-ISR) have demonstrated remarkable perceptual quality, yet the balance between fidelity and controllability remains a problem: multi-step diffusion-based methods suffer from generative diversity and randomness, resulting in low fidelity, while one-step methods lose control flexibility due to fidelity-specific finetuning. In this paper, we present ODTSR, a one-step diffusion transformer based on Qwen-Image that performs Real-ISR considering fidelity and controllability simultaneously: a newly introduced visual stream receives low-quality images (LQ) with adjustable noise (Control Noise), and the original visual stream receives LQs with consistent noise (Prior Noise), forming the Noise-hybrid Visual Stream (NVS) design. ODTSR further employs Fidelity-aware Adversarial Training (FAA) to enhance controllability and achieve one-step inference. Extensive experiments demonstrate that ODTSR not only achieves state-of-the-art (SOTA) performance on generic Real-ISR, but also enables prompt controllability on challenging scenarios such as real-world scene text image super-resolution (STISR) of Chinese characters without training on specific datasets.