Zhiqiang Lang

TL;DR: The AIM 2020 challenge on efficient single image super-resolution was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images with focus on the proposed solutions and results.

TL;DR: The AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results as discussed by the authors was held in 2019, where the goal was to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption.

TL;DR: The AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results as mentioned in this paper had three tracks, Track 1 aims to reduce the amount of parameters while being constrained to maintain or improve the running time and the PSNR result, Track 2 and Track 3 aim to optimize running time with constrain of the other two aspects, respectively.

TL;DR: The ARAD_1K dataset as discussed by the authors is a large-scale RGB image dataset with 1,000 images, which was used for the third biennial challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral information from a 3-channel RGB image.

TL;DR: This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.