Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration challenging. Existing research lacks sufficient focus on these issues, as both problems often coexist in practice. To address this, we design a degradation pipeline that simulates the coexistence of HMB and generic noise, generating synthetic degraded data to train our proposed HAODiff, a human-aware one-step diffusion. Specifically, we propose a triple-branch dual-prompt guidance (DPG), which leverages high-quality images, residual noise (LQ minus HQ), and HMB segmentation masks as training targets. It produces a positive-negative prompt pair for classifier-free guidance (CFG) in a single diffusion step. The resulting adaptive dual prompts let HAODiff exploit CFG more effectively, boosting robustness against diverse degradations. For fair evaluation, we introduce MPII-Test, a benchmark rich in combined noise and HMB cases. Extensive experiments show that our HAODiff surpasses existing state-of-the-art (SOTA) methods in terms of both quantitative metrics and visual quality on synthetic and real-world datasets, including our introduced MPII-Test. Code is available at: https://github.com/gobunu/HAODiff.

翻译：在传输过程中，以人物为中心的图像常遭受严重的通用退化，并易出现人体运动模糊（HMB），使得复原极具挑战性。现有研究对此类问题关注不足，因为这两种问题在实践中常同时存在。为解决此问题，我们设计了一个退化流程，模拟HMB与通用噪声的共存状态，生成合成退化数据以训练我们提出的HAODiff——一种人体感知的单步扩散模型。具体而言，我们提出了一种三分支双提示引导（DPG）机制，该机制以高质量图像、残差噪声（低质量图像减去高质量图像）及HMB分割掩码作为训练目标，在单步扩散中生成用于无分类器引导（CFG）的正负提示对。由此产生的自适应双提示使HAODiff能更有效地利用CFG，从而提升对多种退化类型的鲁棒性。为进行公平评估，我们构建了MPII-Test基准数据集，其中包含大量混合噪声与HMB的案例。大量实验表明，无论是在合成数据集还是真实数据集（包括我们提出的MPII-Test）上，我们的HAODiff在定量指标与视觉质量方面均超越了现有的最先进（SOTA）方法。代码发布于：https://github.com/gobunu/HAODiff。