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

TL;DR

This paper reviews the NTIRE 2026 challenge on real-world single-image reflection removal, introducing a new dataset and showcasing advanced methods that improve reflection removal performance in practical scenarios.

Contribution

It presents the OpenRR-5k dataset for real-world reflection removal and reports on the challenge results that push the state-of-the-art in this task.

Findings

Top methods achieved significant improvements in reflection removal quality.

The OpenRR-5k dataset enables better evaluation of real-world reflection removal methods.

The challenge attracted over 100 registrations, with 11 final participants.

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. This dataset requires participants to process real-world images covering a range of reflection scenarios and intensities, aiming to generate clean images without reflections. The challenge attracted more than 100 registrations, with eleven 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 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.