NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods

2026-04-11

AI Summary

This work addresses the performance gap between existing single-image reflection removal methods and real-world applicability, which stems from their reliance on synthetic or limited real data. To bridge this gap, the study organizes the first large-scale international challenge and introduces OpenRR-5k, a high-quality dataset comprising 5,000 real image pairs with authentic reflections. An expert evaluation protocol is established to rigorously assess method effectiveness. Leveraging a deep learning-based image restoration framework that integrates physically informed reflection modeling with data-driven training strategies, the challenge attracted over 100 participating teams, with 11 finalists selected for comprehensive evaluation. The top-performing approaches demonstrate substantial improvements in reflection removal under complex real-world conditions and receive unanimous endorsement from five domain experts.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Manipulation
• Machine Learning: Large Multimodal Models (LMMs)

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: Social and technical mechanisms of refusal for web technologies and applications

Abstract

In this paper, we review the NTIRE 2026 challenge on single-image reflection removal (SIRR) in the Wild. SIRR is a fundamental task in image restoration. Despite progress in academic research, most methods are tested on synthetic images or limited real-world images, creating a gap in real-world applications. In this challenge, we provide participants with the OpenRR-5k dataset, which requires them to process real-world images that cover a range of reflection scenarios and intensities, with the goal of generating clean images without reflections. The challenge attracted more than 100 registrations, with 11 of them participating in the final testing phase. The top-ranked methods advanced the state-of-the-art reflection removal performance and earned unanimous recognition from the five experts in the field. The proposed OpenRR-5k dataset is available at https://huggingface.co/datasets/qiuzhangTiTi/OpenRR-5k, and the homepage of this challenge is at https://github.com/caijie0620/OpenRR-5k. Due to page limitations, this article only presents partial content; the full report and detailed analyses are available in the extended arXiv version.

Problem

• single image reflection removal
• real-world images
• image restoration
• reflection removal in the wild

Innovation

• single-image reflection removal
• in-the-wild
• OpenRR-5k dataset
• image restoration
• real-world benchmark