The atmospheric and water turbulence mitigation problems have emerged as challenging inverse problems in computer vision and optics communities over the years. However, current methods either rely heavily on the quality of the training dataset or fail to generalize over various scenarios, such as static scenes, dynamic scenes, and text reconstructions. We propose a general implicit neural representation for unsupervised atmospheric and water turbulence mitigation (NeRT). NeRT leverages the implicit neural representations and the physically correct tilt-then-blur turbulence model to reconstruct the clean, undistorted image, given only dozens of distorted input images. Moreover, we show that NeRT outperforms the state-of-the-art through various qualitative and quantitative evaluations of atmospheric and water turbulence datasets. Furthermore, we demonstrate the ability of NeRT to eliminate uncontrolled turbulence from real-world environments. Lastly, we incorporate NeRT into continuously captured video sequences and demonstrate $48 \times$ speedup.

翻译：大气与水体湍流抑制问题多年来已成为计算机视觉与光学领域中极具挑战性的逆问题。然而，现有方法要么严重依赖训练数据集的品质，要么难以在静态场景、动态场景及文本重建等多样化场景中实现泛化。我们提出一种用于无监督大气与水体湍流抑制的通用隐式神经表示方法（NeRT）。NeRT借助隐式神经表示与物理正确的“先倾斜后模糊”湍流模型，仅需数十张失真输入图像即可重建清晰无畸变的图像。此外，通过在大气与水体湍流数据集上的多维度定性与定量评估，我们证明NeRT的性能超越了当前最优方法。进一步，我们展示了NeRT消除真实环境中不可控湍流的能力。最后，我们将NeRT集成至连续视频序列，实现了48倍的加速效果。