Single image super resolution via curvelet based directional dictionaries
Paper ID : 1125-MVIP2020
elhameh mikaeli *, Ali Aghagolzadeh, Masoumeh Azghani
Learning and reconstruction_based methods are two main approaches to solve the single image super resolution (SISR) problem. In this paper we learn the external directional dictionaries (EDD) from external high quality images. Also, we embed the nonlocal means (NLM) filter and an isotropic total variation (TV) scheme in the reconstruction based method. We suggest a new supervised clustering scheme via curvelet based direction extraction method (CCDE) to learn the (EED) from candidate patches with sharp edges. Each input patch is coded by all EDD. Each of the reconstructed patches under different EDD is applied with a weighted penalty to characterize the given input patch. To disclose new details, the local smoothness and nonlocal self_similarity priors are added on the recovered patch by TV scheme and NLM filter, respectively. Extensive experimental results validate the effectiveness and robustness of the proposed methods.
single image super-resolution, spare representation, directional features, local smoothness, nonlocal_selfsimilarity
Status : Paper Accepted (Oral Presentation)