The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results

2026-04-12

AI Summary

This work addresses the challenge of facial image degradation in real-world scenarios by organizing and systematically evaluating a diverse set of face restoration methods under no constraints on computational resources or training data. A comprehensive benchmarking framework is established by integrating weighted image quality assessment (IQA) metrics with the AdaFace identity consistency verification model, effectively balancing perceptual quality, photorealism, and identity preservation. The competition attracted 96 registered teams, of which 10 submitted valid solutions and 9 achieved meaningful rankings. This effort has significantly advanced the development of high-fidelity face restoration techniques and provides a consolidated summary of current trends and practical benchmarks in the field.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural and realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. Performance is evaluated using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 96 registrants, with 10 teams submitting valid models; ultimately, 9 teams achieved valid scores in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

Problem

• real-world face restoration
• identity consistency
• perceptual quality
• realism
• image quality assessment

Innovation

• real-world face restoration
• identity consistency
• perceptual quality
• AdaFace
• image quality assessment