An Improved PDE Based Super-Resolution Reconstruction Algorithm

AbstractIn this paper, we present an improved partial differential equation (PDE) model for multi-frame image superresolution reconstruction. Our proposed PDE model is achieved by using an adaptively weighting function, which combines the Total Variation (TV) regularization with fourth-order partial differential equations (PDE) regularization. Experiments show the effectiveness and practicability of the proposed method and demonstrate its superiority to some existing SR methods, both in its visual effects and in quantitative terms