发布真实场景反光去除数据集，推动图像去反光技术落地。
NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods
- 构建真实世界反光图像数据集OpenRR-5k，覆盖多种反光场景。
- 11支队伍参与挑战，顶尖方法显著提升去反光性能。
- 适合关注真实图像修复与计算机视觉应用的研究者。
本文回顾了NTIRE 2026年关于真实世界单图反光去除（SIRR）的挑战赛。SIRR是图像复原的基础任务，尽管学术研究取得进展，但多数方法仅在合成图像或有限真实图像上测试，难以满足实际应用需求。为此，本挑战赛发布了OpenRR-5k数据集，包含大量真实世界图像，涵盖不同反光强度与场景，要求参赛者生成无反光的干净图像。挑战赛吸引了超过100名注册者，其中11支队伍进入最终测试阶段。排名靠前的方法显著提升了去反光性能，获得领域内五位专家的一致认可。OpenRR-5k数据集已公开于https://huggingface.co/datasets/qiuzhangTiTi/OpenRR-5k，挑战赛主页为https://github.com/caijie0620/OpenRR-5k。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。