_version_ 1866908974790475776
author Cai, Jie
Yang, Kangning
Li, Zhiyuan
Vasluianu, Florin-Alexandru
Timofte, Radu
Li, Jinlong
Shen, Jinglin
Meng, Zibo
Cao, Junyan
Zhao, Lu
Liu, Pengwei
Zhang, Yuyi
Guo, Fengjun
Hu, Jiagao
Wang, Zepeng
Wang, Fei
Zhou, Daiguo
Chen, Yi'ang
Zhu, Honghui
Yang, Mengru
Luo, Yan
Jiang, Kui
Guo, Jin
Park, Jonghyuk
Sim, Jae-Young
Zhou, Wei
Huang, Hongyu
Li, Linfeng
Kong, Lindong
Meesiyawar, Saiprasad
Khanpagadi, Misbha Falak
Akalwadi, Nikhil
Tabib, Ramesh Ashok
Mudenagudi, Uma
Benjdira, Bilel
Ali, Anas M.
Boulila, Wadii
Shigematsu, Kosuke
Shirono, Hiroto
Shin, Asuka
Xu, Guoyi
Jiang, Yaoxin
Liu, Jiajia
Shi, Yaokun
Tu, Jiachen
Joshi, Shreeniketh
Jiang, Jin-Hui
Lin, Yu-Fan
Hsiao, Yu-Jou
Lee, Chia-Ming
Yang, Fu-En
Wang, Yu-Chiang Frank
Hsu, Chih-Chung
author_facet Cai, Jie
Yang, Kangning
Li, Zhiyuan
Vasluianu, Florin-Alexandru
Timofte, Radu
Li, Jinlong
Shen, Jinglin
Meng, Zibo
Cao, Junyan
Zhao, Lu
Liu, Pengwei
Zhang, Yuyi
Guo, Fengjun
Hu, Jiagao
Wang, Zepeng
Wang, Fei
Zhou, Daiguo
Chen, Yi'ang
Zhu, Honghui
Yang, Mengru
Luo, Yan
Jiang, Kui
Guo, Jin
Park, Jonghyuk
Sim, Jae-Young
Zhou, Wei
Huang, Hongyu
Li, Linfeng
Kong, Lindong
Meesiyawar, Saiprasad
Khanpagadi, Misbha Falak
Akalwadi, Nikhil
Tabib, Ramesh Ashok
Mudenagudi, Uma
Benjdira, Bilel
Ali, Anas M.
Boulila, Wadii
Shigematsu, Kosuke
Shirono, Hiroto
Shin, Asuka
Xu, Guoyi
Jiang, Yaoxin
Liu, Jiajia
Shi, Yaokun
Tu, Jiachen
Joshi, Shreeniketh
Jiang, Jin-Hui
Lin, Yu-Fan
Hsiao, Yu-Jou
Lee, Chia-Ming
Yang, Fu-En
Wang, Yu-Chiang Frank
Hsu, Chih-Chung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10321
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods
Cai, Jie
Yang, Kangning
Li, Zhiyuan
Vasluianu, Florin-Alexandru
Timofte, Radu
Li, Jinlong
Shen, Jinglin
Meng, Zibo
Cao, Junyan
Zhao, Lu
Liu, Pengwei
Zhang, Yuyi
Guo, Fengjun
Hu, Jiagao
Wang, Zepeng
Wang, Fei
Zhou, Daiguo
Chen, Yi'ang
Zhu, Honghui
Yang, Mengru
Luo, Yan
Jiang, Kui
Guo, Jin
Park, Jonghyuk
Sim, Jae-Young
Zhou, Wei
Huang, Hongyu
Li, Linfeng
Kong, Lindong
Meesiyawar, Saiprasad
Khanpagadi, Misbha Falak
Akalwadi, Nikhil
Tabib, Ramesh Ashok
Mudenagudi, Uma
Benjdira, Bilel
Ali, Anas M.
Boulila, Wadii
Shigematsu, Kosuke
Shirono, Hiroto
Shin, Asuka
Xu, Guoyi
Jiang, Yaoxin
Liu, Jiajia
Shi, Yaokun
Tu, Jiachen
Joshi, Shreeniketh
Jiang, Jin-Hui
Lin, Yu-Fan
Hsiao, Yu-Jou
Lee, Chia-Ming
Yang, Fu-En
Wang, Yu-Chiang Frank
Hsu, Chih-Chung
Computer Vision and Pattern 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.
title NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10321