PROJECT TITLE :

Joint Non Gaussian Denoising and Superresolving of Raw High Frame Rate Videos - 2014

ABSTRACT:

High frame rate cameras capture sharp videos of highly dynamic scenes by trading off signal-noise-ratio and image resolution, therefore combinational super-resolving and denoising is crucial for enhancing high speed videos and increasing their applications. The solution is nontrivial thanks to the fact that two deteriorations co-occur during capturing and noise is nonlinearly addicted to signal strength. To handle this drawback, we propose conducting noise separation and super resolution underneath a unified optimization framework, that models both spatiotemporal priors of top quality videos and signal-dependent noise. Mathematically, we align the frames along temporal axis and pursue the answer beneath the subsequent 3 criterion: one) the sharp noise-free image stack is low rank with some missing pixels denoting occlusions; 2) the noise follows a given nonlinear noise model; and 3) the recovered sharp image will be reconstructed well with sparse coefficients and an over complete dictionary learned from prime quality natural pictures. In computation aspects, we tend to propose to get the final result by solving a convex optimization using the modern local linearization techniques. In the experiments, we tend to validate the proposed approach in both synthetic and real captured information.