The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

2026-04-19

AI Summary

This work addresses the challenge of real-world image super-resolution under unknown degradation by introducing, for the first time, a mobile-oriented competition track that requires participating methods to balance reconstruction quality and inference efficiency at a ×4 upscaling factor. A weighted composite metric combining image quality assessment scores and speedup ratios is employed for ranking, thereby promoting the development of lightweight, efficient, and robust super-resolution models. The competition attracted 108 registered teams, with 16 submitting valid solutions, significantly advancing the performance frontier of mobile real-image super-resolution and offering a systematic overview of the latest technical trends in this domain.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multi-Robot Systems

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through unknown degradations with a x4 scaling factor while ensuring the models remain executable on mobile devices. The objective is to develop effective and efficient network designs or solutions that achieve state-of-the-art real-world image super-resolution performance. The track of the challenge evaluates performance using a weighted combination of image quality assessment (IQA) score and speedup ratios. The competition attracted 108 registrants, with 16 teams achieving a valid score in the final ranking. This collaborative effort advances the performance of mobile real-world image super-resolution while offering an in-depth overview of the latest trends in the field.

Problem

• mobile super-resolution
• real-world image super-resolution
• unknown degradations
• efficient model
• x4 scaling

Innovation

• mobile super-resolution
• real-world image restoration
• efficient network design
• unknown degradation
• NTIRE challenge