The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

TL;DR

The NTIRE 2026 challenge on infrared image super-resolution benchmarks current methods, introduces a dataset, and evaluates solutions to enhance high-resolution remote sensing infrared images from low-resolution inputs.

Contribution

This paper presents the first NTIRE challenge on infrared image super-resolution, including dataset, evaluation protocol, and analysis of top-performing methods.

Findings

115 participants registered, 13 teams submitted valid entries

Benchmark results highlight the effectiveness of recent super-resolution techniques

The challenge promotes progress in real-world infrared remote sensing applications

Abstract

This paper presents the NTIRE 2026 Remote Sensing Infrared Image Super-Resolution (x4) Challenge, one of the associated challenges of NTIRE 2026. The challenge aims to recover high-resolution (HR) infrared images from low-resolution (LR) inputs generated through bicubic downsampling with a x4 scaling factor. The objective is to develop effective models or solutions that achieve state-of-the-art performance for infrared image SR in remote sensing scenarios. To reflect the characteristics of infrared data and practical application needs, the challenge adopts a single-track setting. A total of 115 participants registered for the competition, with 13 teams submitting valid entries. This report summarizes the challenge design, dataset, evaluation protocol, main results, and the representative methods of each team. The challenge serves as a benchmark to advance research in infrared image super-resolution and promote the development of effective solutions for real-world remote sensing applications.