NTIRE 2024 Challenge on Image Super-Resolution (×4): Methods and Results

This paper reviews the NTIRE 2024 challenge on image super-resolution (×4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.

1. Introduction

Single image super-resolution (SR) involves the recovery of high-resolution (HR) images from single low-resolution (LR) inputs subjected to a certain degradation process. Image SR is applicable across a variety of visual tasks and application scenarios [45], [75]. As such, interest in this task has escalated in both academic and industrial sectors. Recently, a continuous stream of methods has been proposed, particularly emphasizing those based on deep neural networks [10], [13], [19], [41], [63], [95].