Advances and challenges in super‐resolution

Sina Farsiu, D. Robinson, Michael Elad, Peyman Milanfar

International Journal of Imaging Systems and Technology · 2004 · 617 citations · 53 references

Concepts

TL;DR

Super‑Resolution reconstruction generates high‑resolution images from a sequence of low‑resolution frames. This review surveys Super‑Resolution methods from the past two decades, summarizes the authors’ recent contributions, and outlines future challenges. The authors analyze robustness, color handling, and dynamic operation modes, and propose novel methods validated by experiments on simulated and real data. Experimental results on simulated and real data demonstrate the effectiveness of the novel methods. © 2004 Wiley Periodicals, Inc.; DOI 10.1002/ima.20007.

Abstract

Abstract Super‐Resolution reconstruction produces one or a set of high‐resolution images from a sequence of low‐resolution frames. This article reviews a variety of Super‐Resolution methods proposed in the last 20 years, and provides some insight into, and a summary of, our recent contributions to the general Super‐Resolution problem. In the process, a detailed study of several very important aspects of Super‐Resolution, often ignored in the literature, is presented. Specifically, we discuss robustness, treatment of color, and dynamic operation modes. Novel methods for addressing these issues are accompanied by experimental results on simulated and real data. Finally, some future challenges in Super‐Resolution are outlined and discussed. © 2004 Wiley Periodicals, Inc. Int J Imaging Syst Technol 14, 47–57, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.20007

References

53