The Fourth Challenge on Image Super-Resolution ($\times$4) at NTIRE 2026: Benchmark Results and Method Overview

2026-04-15

AI Summary

This study addresses high-fidelity and perceptually realistic super-resolution reconstruction from low-resolution images generated via bicubic downscaling. To comprehensively evaluate competing approaches, the work establishes a unified benchmark comprising two tracks: one optimized for pixel-level fidelity measured by PSNR, and the other for visual realism assessed through perceptual quality metrics. The benchmark attracted 194 participants and 31 teams submitting valid solutions, effectively aggregating state-of-the-art super-resolution methods. This effort not only enables thorough technical comparison across diverse algorithmic strategies but also systematically outlines emerging trends in the field, thereby establishing itself as a pivotal and authoritative reference for super-resolution research.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Applications

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Large-scale security measurements

Abstract

This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective super-resolution solutions and analyze recent advances in the field. To reflect the evolving objectives of image super-resolution, the challenge includes two tracks: (1) a restoration track, which emphasizes pixel-wise fidelity and ranks submissions based on PSNR; and (2) a perceptual track, which focuses on visual realism and evaluates results using a perceptual score. A total of 194 participants registered for the challenge, with 31 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, main results, and methods of participating teams. The challenge provides a unified benchmark and offers insights into current progress and future directions in image super-resolution.

Problem

• image super-resolution
• bicubic downsampling
• pixel-wise fidelity
• perceptual realism
• ×4 scaling

Innovation

• image super-resolution
• perceptual quality
• PSNR
• bicubic downsampling
• benchmark