基于帧共享退化参数的物理驱动大气湍流去除
Physically-Grounded Turbulence Mitigation with Frame-Shared Degradation Parameters
把「倾斜-再模糊」物理退化模型参数化为场景共享相关函数加逐帧噪声图，为视频/多帧复原中退化参数估计的病态性提供了一种跨帧共享的优化式解法，可迁移到其他逐帧退化估计任务。
原文依据 By decomposing the distortion and blur of each frame into a scene-shared correlation function and per-frame noise maps
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大气湍流会在远距离成像中造成空间变化的畸变与模糊，使真实场景下的复原极具挑战。有监督方法依赖合成训练数据，而其模拟的退化往往无法忠实反映真实湍流。现有无监督方法通常对每一帧独立估计退化参数，未能利用同一场景各帧之间共享的相关性。我们提出 TMFS，一种基于优化且物理驱动的方法，用于无监督湍流复原。TMFS 基于具有物理动机的「先倾斜后模糊」退化模型，并通过共享的湍流结构来表示各帧退化。通过将每一帧的畸变与模糊分解为场景共享的相关函数和逐帧噪声图，TMFS 实现了跨帧信息共享，并缓解了逐帧估计的病态性。在合成与真实数据集上的实验证明了 TMFS 的有效性及其对真实湍流的强泛化能力。
英文原文摘要 1070 字符
Atmospheric turbulence causes spatially varying distortion and blur in long-range imaging, making restoration highly challenging in real-world applications. Supervised methods rely on synthetic training data, whose simulated degradation often cannot faithfully reflect real turbulence. Existing unsupervised methods usually estimate degradation parameters for each frame independently, without exploiting the shared correlations among frames from the same scene. We propose TMFS, an optimization-based and physics-grounded method for unsupervised turbulence restoration. TMFS is based on a physically motivated tilt-then-blur degradation model and represents frame degradations through a shared turbulence structure. By decomposing the distortion and blur of each frame into a scene-shared correlation function and per-frame noise maps, TMFS enables cross-frame information sharing and alleviates the ill-posedness of framewise estimation. Experiments on synthetic and real datasets demonstrate the effectiveness of TMFS and its strong generalization to real turbulence.