A Nuclear-norm Model for Multi-Frame Super-Resolution Reconstruction from Video Clips

TL;DR

This paper introduces a variational method using nuclear-norm regularization for multi-frame super-resolution from video clips, achieving more accurate and detailed high-resolution images with fewer artifacts.

Contribution

It presents a novel nuclear-norm based low-rank model combined with optical flow for super-resolution, solved via ADMM, improving image quality over existing methods.

Findings

More accurate high-resolution images with fewer artifacts

Finer and more discernible details in reconstructed images

Effective on both synthetic and real video clips

Abstract

We propose a variational approach to obtain super-resolution images from multiple low-resolution frames extracted from video clips. First the displacement between the low-resolution frames and the reference frame are computed by an optical flow algorithm. Then a low-rank model is used to construct the reference frame in high-resolution by incorporating the information of the low-resolution frames. The model has two terms: a 2-norm data fidelity term and a nuclear-norm regularization term. Alternating direction method of multipliers is used to solve the model. Comparison of our methods with other models on synthetic and real video clips show that our resulting images are more accurate with less artifacts. It also provides much finer and discernable details.