Generalizing the Nonlocal-Means to Super-Resolution Reconstruction

TLDR

Super‑resolution reconstruction fuses multiple low‑quality images into a higher‑resolution result, but accurate motion estimation is essential; inaccurate motion, common with non‑global fields, produces artifacts. We aim to develop a super‑resolution algorithm that, like recent video denoising methods, operates without explicit motion estimation and can handle general motion patterns. The method generalizes the Nonlocal‑Means denoising algorithm into a simple super‑resolution framework that does not require motion estimation. Experiments on several test movies demonstrate that the proposed algorithm successfully produces super‑resolved images for general motion sequences.

Abstract

Super-resolution reconstruction proposes a fusion of several low-quality images into one higher quality result with better optical resolution. Classic super-resolution techniques strongly rely on the availability of accurate motion estimation for this fusion task. When the motion is estimated inaccurately, as often happens for nonglobal motion fields, annoying artifacts appear in the super-resolved outcome. Encouraged by recent developments on the video denoising problem, where state-of-the-art algorithms are formed with no explicit motion estimation, we seek a super-resolution algorithm of similar nature that will allow processing sequences with general motion patterns. In this paper, we base our solution on the Nonlocal-Means (NLM) algorithm. We show how this denoising method is generalized to become a relatively simple super-resolution algorithm with no explicit motion estimation. Results on several test movies show that the proposed method is very successful in providing super-resolution on general sequences.