MétaCan
Menu
Back to cohort
Record W4414197797 · doi:10.1109/cvprw67362.2025.00122

NTIRE 2025 Challenge on Single Image Reflection Removal in the Wild: Datasets, Methods and Results

2025· article· en· W4414197797 on OpenAlexaff
Kangning Yang, Jie Cai, Ling Ouyang, Florin-Alexandru Vasluianu, Radu Timofte, Jiaming Ding, Huiming Sun, Lan Fu, Jinlong Li, Chiu Man Ho, Zibo Meng, Mingjia Li, Hanxiao Wang, Qiming Hu, Hao Zhao, Jin Hu, Xiaojie Guo, Kui Jiang, Jin Guo, Junjun Jiang, Jing He, Yiqing Wang, Kexin Zhang, Licheng Jiao, Lingling Li, Fang Liu, Wenping Ma, Zhiyang Chen, Hao Fang, Wei Zhang, Runmin Cong, Dheeraj Damodhar Hegde, Jatin Kalal, Nikhil Akalwadi, Ramesh Ashok Tabib, Uma Mudenagudi, Yu-Fan Lin, Chia-Ming Lee, Chih–Chung Hsu, Xiaochao Qu, Luoqi Liu, Ting Liu, Jinshan Chen, S. He, K. Uma, A Sasithradevi, B Sathya Bama, S. Mohamed Mansoor Roomi, Bilel Benjdira, Anas M. Ali, Wadii Boulila, Wei Dong, Yunzhe Li, Ali Hussein, Han Zhou, Jun Chen, Zeyu Xiao, Zhuoyuan Li

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicImage Enhancement Techniques
Canadian institutionsMcMaster University
FundersAlexander von Humboldt-Stiftung
KeywordsReflection (computer programming)Process (computing)Cover (algebra)Task (project management)Image (mathematics)Range (aeronautics)

Abstract

fetched live from OpenAlex

In this paper, we review the NTIRE 2025 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 realworld applications. In this challenge, participants are required 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 200 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 datasets are available at https://huggingface.co/datasets/qiuzhangTiTi/NTIRE2025-SIRR and the homepage of this challenge is at https://github.com/caijie0620/Reflection-Removal-in-thewild.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.008
metaresearch head score (Gemma)0.015
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.016
Threshold uncertainty score0.040

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.015
Meta-epidemiology (narrow)0.0070.001
Meta-epidemiology (broad)0.0040.004
Bibliometrics0.0040.003
Science and technology studies0.0020.002
Scholarly communication0.0040.005
Open science0.0060.006
Research integrity0.0050.004
Insufficient payload (model declined to judge)0.0090.023

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.044
GPT teacher head0.397
Teacher spread0.352 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreOther

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations29
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicImage Enhancement TechniquesFrench-language works237,207