We present a method to enhance the quality of a video sequence captured through a turbulent atmospheric medium. Enhancement is framed as the inference of the radiance of the distant scene, represented as a latent image," that is assumed to be constant throughout the video. Temporal distortion is thus zero-mean and temporal averaging produces a blurred version of the scene's radiance, that is processed via a Sobolev gradient flow to yield the latent image in a way that is reminiscent of the lucky region" method. Without enforcing prior knowledge, we can stabilize the video sequence while preserving ne details. We also present the well-posedness theory for the stabilizing PDE and a linear stability analysis of the numerical scheme. This is a joint work with Sung Ha Kang, Stefano Soatto and Andrea Bertozzi.