AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results

TL;DR

This paper reviews the AIM 2019 challenge on constrained super-resolution, highlighting innovative solutions and results across three tracks focused on balancing model size, speed, and image quality.

Contribution

It presents a comprehensive overview of the challenge's solutions, emphasizing methods that optimize super-resolution under various constraints.

Findings

Multiple teams achieved improved super-resolution performance.

Trade-offs between model size, speed, and fidelity were systematically analyzed.

The challenge set new benchmarks for constrained super-resolution methods.

Abstract

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.