D$^2$-VR: 降质鲁棒且蒸馏的视频修复与协同优化策略
D$^2$-VR: Degradation-Robust and Distilled Video Restoration with Synergistic Optimization Strategy
AI总结：
D$^2$-VR通过降质鲁棒流对齐和对抗蒸馏技术，实现低步推理的视频修复，提升修复质量和效率。
摘要：
扩散先验与时间对齐的结合已成为视频修复的一种变革性范式，能够提供出色的感知质量，但此类框架的实际部署受到抑制的推理延迟和时间不稳定性的严重限制，尤其是在面对复杂现实降质时。为了解决这些限制，我们提出了D$^2$-VR，一种基于单图像扩散的视频修复框架，具有低步推理。为了在严重降质下获得精确的时间引导，我们首先设计了一个降质鲁棒流对齐（DRFA）模块，该模块利用信心感知注意力来过滤不可靠的运动提示。然后，我们引入了对抗蒸馏范式，将扩散采样轨迹压缩到快速的少量步骤中。最后，设计了一种协同优化策略，以协调感知质量和严格的时间一致性。大量实验表明，D$^2$-VR在加速采样过程方面实现了12×的提升，同时达到了最先进的性能。
英文摘要：
The integration of diffusion priors with temporal alignment has emerged as a transformative paradigm for video restoration, delivering fantastic perceptual quality, yet the practical deployment of such frameworks is severely constrained by prohibitive inference latency and temporal instability when confronted with complex real-world degradations. To address these limitations, we propose \textbf{D$^2$-VR}, a single-image diffusion-based video-restoration framework with low-step inference. To obtain precise temporal guidance under severe degradation, we first design a Degradation-Robust Flow Alignment (DRFA) module that leverages confidence-aware attention to filter unreliable motion cues. We then incorporate an adversarial distillation paradigm to compress the diffusion sampling trajectory into a rapid few-step regime. Finally, a synergistic optimization strategy is devised to harmonize perceptual quality with rigorous temporal consistency. Extensive experiments demonstrate that D$^2$-VR achieves state-of-the-art performance while accelerating the sampling process by \textbf{12$\times$}
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。
