A novel theoretical analysis on optimal pipeline of multi-frame image super-resolution using sparse coding

Mohammad Mahdi Afrasiabi, Reshad Hosseini, Aliazam Abbasfar

Abstract: Highlights•Our theoretical analysis uses sparse coding (SC) and iterative shrinkage-thresholding algorithm.•Our analysis fills the gap of mathematical justification in execution order of optimal multi-frame super-resolution (MFSR) pipeline.•Our analysis recommends to perform alignment and fusion before the reconstruction stage, whether through deconvolution or single image super-resolution (SISR) techniques.•Optimal pipeline has much lower computational than intuitive approaches that apply SISR method to each input LR image.•We demonstrate the usefulness of SC in analysis of computer vision tasks such as MFSR, leveraging the sparsity assumption in natural images.