NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

2026-04-13

AI Summary

This work addresses the challenge that existing image restoration models struggle to simultaneously achieve effective noise suppression, fine detail preservation, and accurate color and illumination fidelity in real-world low-light portrait scenarios. To this end, the authors launch the AI Flash Portrait Challenge, introducing a high-quality benchmark dataset comprising 800 real low-light portrait image pairs—the first of its kind—and incorporating portrait mask-guided training and evaluation protocols. A hybrid assessment framework combining objective metrics and subjective human evaluation is employed to comprehensively benchmark algorithmic performance. The challenge attracted over 100 participating teams, yielding more than 3,000 valid submissions. The released dataset and baseline code have significantly advanced research and practical applications in low-light portrait enhancement.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Crowd Sourcing and Human Computation

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
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite significant advancements in deep learning for image restoration, existing models still encounter substantial challenges in real-world low-light portrait scenarios. Specifically, they struggle to achieve an optimal balance among noise suppression, detail preservation, and faithful illumination and color reproduction. To bridge this gap, this challenge aims to establish a novel benchmark for real-world low-light portrait restoration. We comprehensively evaluate the proposed algorithms utilizing a hybrid evaluation system that integrates objective quantitative metrics with rigorous subjective assessment protocols. For this competition, we provide a dataset containing 800 groups of real-captured low-light portrait data. Each group consists of a 1K-resolution low-light input image, a 1K ground truth (GT), and a 1K person mask. This challenge has garnered widespread attention from both academia and industry, attracting over 100 participating teams and receiving more than 3,000 valid submissions. This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition. The released dataset and baseline code for this track are publicly available from the same \href{https://github.com/zsn1434/AI_Flash-BaseLine/tree/main}{GitHub repository}, and the official challenge webpage is hosted on \href{https://www.codabench.org/competitions/12885/}{CodaBench}.

Problem

• low-light portrait restoration
• noise suppression
• detail preservation
• illumination reproduction
• color fidelity

Innovation

• low-light portrait restoration
• real-world image dataset
• hybrid evaluation system
• AI Flash Portrait
• image enhancement benchmark