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

TL;DR

This paper reviews the NTIRE 2026 challenge on real-world face restoration, detailing solutions, results, and current trends to improve perceptual quality and identity preservation in face restoration tasks.

Contribution

It provides an overview of the challenge's solutions, results, and insights into the latest advancements in real-world face restoration techniques.

Findings

Nine teams achieved valid scores in the final ranking.

The challenge attracted 96 registrants and 10 valid submissions.

Performance was evaluated using a weighted IQA score and AdaFace as an identity checker.

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.