IVCVMay 3, 2020

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

arXiv:2005.01056v152 citations
Originality Synthesis-oriented
AI Analysis

This challenge benchmarks and advances methods for high-quality image super-resolution, relevant for applications in computer vision and image processing, but is incremental as it builds on existing competition frameworks.

The paper reviewed the NTIRE 2020 challenge on perceptual extreme super-resolution, where participants developed methods to upscale images by a factor of 16, with 19 teams submitting final results to gauge state-of-the-art performance.

This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes