We address the problem of restoring a high-quality image from an observed\nimage sequence strongly distorted by atmospheric turbulence. A novel algorithm\nis proposed in this paper to reduce geometric distortion as well as\nspace-and-time-varying blur due to strong turbulence. By considering a suitable\nenergy functional, our algorithm first obtains a sharp reference image and a\nsubsampled image sequence containing sharp and mildly distorted image frames\nwith respect to the reference image. The subsampled image sequence is then\nstabilized by applying the Robust Principal Component Analysis (RPCA) on the\ndeformation fields between image frames and warping the image frames by a\nquasiconformal map associated with the low-rank part of the deformation matrix.\nAfter image frames are registered to the reference image, the low-rank part of\nthem are deblurred via a blind deconvolution, and the deblurred frames are then\nfused with the enhanced sparse part. Experiments have been carried out on both\nsynthetic and real turbulence-distorted video. Results demonstrate that our\nmethod is effective in alleviating distortions and blur, restoring image\ndetails and enhancing visual quality.\n