NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study

TLDR

The NTIRE 2017 challenge was the first of its kind, featuring six competitions, hundreds of participants, and dozens of proposed solutions. The paper introduces a large dataset for example‑based single image super‑resolution and evaluates state‑of‑the‑art methods from the NTIRE 2017 challenge. The authors used the newly collected DIV2K dataset to compare challenge solutions with representative literature methods, evaluating them with diverse metrics and conducting additional experiments on various topics. The challenge advances the state‑of‑the‑art, achieving the best results to date on Set5, Set14, B100, Urban100, and the DIV2K dataset.

Abstract

This paper introduces a novel large dataset for example-based single image super-resolution and studies the state-of-the-art as emerged from the NTIRE 2017 challenge. The challenge is the first challenge of its kind, with 6 competitions, hundreds of participants and tens of proposed solutions. Our newly collected DIVerse 2K resolution image dataset (DIV2K) was employed by the challenge. In our study we compare the solutions from the challenge to a set of representative methods from the literature and evaluate them using diverse measures on our proposed DIV2K dataset. Moreover, we conduct a number of experiments and draw conclusions on several topics of interest. We conclude that the NTIRE 2017 challenge pushes the state-of-the-art in single-image super-resolution, reaching the best results to date on the popular Set5, Set14, B100, Urban100 datasets and on our newly proposed DIV2K.