统一视频修复框架，用流匹配和提示引导实现高效通用修复。
UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
- 将修复建模为受提示引导的物理向量场连续演化过程。
- 在去噪任务中达33.89 dB PSNR、0.97 SSIM，性能领先。
- 适合需要跨多种退化类型统一处理的视频修复场景。
视频成像常受模糊、噪声和压缩伪影等复杂退化影响。传统方法采用‘单任务单模型’范式，泛化能力差且计算成本高，难以应对现实场景中多样的退化类型。我们提出UniFlowRestore，一种通用视频修复框架，将修复建模为受提示引导与物理先验约束的连续时间演化过程。物理感知主干PhysicsUNet将退化先验编码为势能，提示生成器（PromptGenerator）产生任务相关提示作为动量。二者共同定义一个哈密顿系统，其向量场融合惯性动力学、衰减物理梯度与提示引导。通过固定步长常微分方程求解器优化，实现跨任务高效统一修复。实验表明，UniFlowRestore在多项任务上达到领先性能，尤其在去噪任务中取得33.89 dB PSNR和0.97 SSIM，且在所有评估任务中保持顶尖或次优表现。
原文摘要 · Abstract (English)
Video imaging is often affected by complex degradations such as blur, noise, and compression artifacts. Traditional restoration methods follow a "single-task single-model" paradigm, resulting in poor generalization and high computational cost, limiting their applicability in real-world scenarios with diverse degradation types. We propose UniFlowRestore, a general video restoration framework that models restoration as a time-continuous evolution under a prompt-guided and physics-informed vector field. A physics-aware backbone PhysicsUNet encodes degradation priors as potential energy, while PromptGenerator produces task-relevant prompts as momentum. These components define a Hamiltonian system whose vector field integrates inertial dynamics, decaying physical gradients, and prompt-based guidance. The system is optimized via a fixed-step ODE solver to achieve efficient and unified restoration across tasks. Experiments show that UniFlowRestore delivers stateof-the-art performance with strong generalization and efficiency. Quantitative results demonstrate that UniFlowRestore achieves state-of-the-art performance, attaining the highest PSNR (33.89 dB) and SSIM (0.97) on the video denoising task, while maintaining top or second-best scores across all evaluated tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。