NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods
This challenge addresses the gap between synthetic and real-world reflection removal for the computer vision community, providing a new benchmark dataset and advancing practical SIRR methods.
The NTIRE 2026 challenge on single-image reflection removal introduced the OpenRR-5k dataset of real-world images, attracting over 100 registrations and 11 final participants. Top methods advanced state-of-the-art performance, earning unanimous expert recognition.
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.