An improved PDE-constrained optimization fluid registration for image multi-frame super resolution

The main idea of multi-frame super resolution (SR) algorithms is to recover a single high-resolution image from sequence low ones the same object. success SR approaches often related well registration and restoration steps. Therefore, we propose new approach based on partial differential equation (PDE)-constrained optimization fluid use fourth order PDE treat both steps that guarantee algorithms. Since step usually variational ill-posed model, mathematical study needed check existence solution regularized problem. Thus, prove posed assure also used second in step. results show proposed method competitive with existing methods.