AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results
This is an incremental benchmarking effort for the computer vision community to advance super-resolution techniques under practical constraints.
The paper reviews the AIM 2019 challenge on constrained single image super-resolution, which had three tracks focusing on reducing parameters, optimizing running time, and improving PSNR while maintaining other aspects, with 12 teams submitting final results to gauge state-of-the-art performance.
This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results. The challenge had 3 tracks. Taking the three main aspects (i.e., number of parameters, inference/running time, fidelity (PSNR)) of MSRResNet as the baseline, Track 1 aims to reduce the amount of parameters while being constrained to maintain or improve the running time and the PSNR result, Tracks 2 and 3 aim to optimize running time and PSNR result with constrain of the other two aspects, respectively. Each track had an average of 64 registered participants, and 12 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.