NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

Xin Li; Yeying Jin; Suhang Yao; Beibei Lin; Zhaoxin Fan; Wending Yan; Xin Jin; Zongwei Wu

cs.CVApr 12, 2026

NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

Authors: Xin Li, Yeying Jin, Suhang Yao, Beibei Lin, Zhaoxin Fan, Wending Yan, Xin Jin, Zongwei Wu, Bingchen Li, Peishu Shi, Yufei Wang, Yu Li, Zhibo Chen, Bihan Wen, Robby T. Tan, Radu Timofte, Runzhe Li, Kui Jiang, Zhaocheng Yu, Yiang Chen, Junjun Jiang, Xianming Liu, Hongde Gu, Zeliang Li, Mache You, Jiangxin Dong, Jinshan Pan, Qiyu Rong, Bowen Shao, Hongyuan Jing, Mengmeng Zhang, Bo Ding, Hui Zhang, Yi Ren, Mohab Kishawy, Jun Chen, Anh-Kiet Duong, Petra Gomez-Kramer, Jean-Michel Carozza, Wangzhi Xing, Xin Lu, Enxuan Gu, Jingxi Zhang, Diqi Chen, Qiaosi Yi, Bingcai Wei, Wenjie Li, Bowen Tie, Heng Guo, Zhanyu Ma, Jiachen Tu, Guoyi Xu, Yaoxin Jiang, Cici Liu, Yaokun Shi, Paula Garrido Mellado, Daniel Feijoo, Alvaro Garcia Lara, Marcos V. Conde, Zhidong Zhu, Bangshu Xiong, Qiaofeng Ou, Zhibo Rao, Wei Li, Zida Zhang, Hui Geng, Qisheng Xu, Xuyao Deng, Changjian Wang, Kele Xu, Guanglu Dong, Qiyao Zhao, Tianheng Zheng, Chunlei Li, Lichao Mou, Chao Ren, Chang-De Peng, Chieh-Yu Tsai, Guan-Cheng Liu, Li-Wei Kang, Abhishek Rajak, Milan Kumar Singh, Ankit Kumar, Dimple Sonone, Kishor Upla, Kiran Raja, Huilin Zhao, Xing Xu, Chuan Chen, Yeming Lao, Wenjing Xun, Li Yang, Bilel Benjdira, Anas M. Ali, Wadii Boulila, Hao Yang, Ruikun Zhang, Liyuan Pan

Abstract

This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this challenge attracted a wide range of impressive solutions, all developed and evaluated on our real-world Raindrop Clarity dataset~\cite{jin2024raindrop}. For this edition, we adjust the dataset with 14,139 images for training, 407 images for validation, and 593 images for testing. The primary goal of this challenge is to establish a strong and practical benchmark for the removal of raindrops under various illumination and focus conditions. In total, 168 teams have registered for the competition, and 17 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the Raindrop Clarity dataset, demonstrating the growing progress in this challenging task.

Figures & tables

Team	Leader	Final Score $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Params. (M)	GFlops (G)	Ensemble	Extra Data	Rank
AIIA–Lab	Runzhe Li	35.2378	28.3392	0.8265	0.2732	16.6	129.9	$\checkmark$	$\otimes$	1
raingod	Hongde Gu	35.2186	28.2817	0.8255	0.2636	16.6	129.9	$\checkmark$	$\checkmark$	2
BUU_CV	Qiyu Rong	35.0360	28.1469	0.8222	0.2665	26.89	42.33	$\checkmark$	$\checkmark$	3
RetinexDualV2	Mohab Kishawy	33.8556	27.2379	0.8061	0.2887	4.8	301.6	$\checkmark$	$\otimes$	4
ULR	Anh–Kiet Duong	33.7505	27.0572	0.7966	0.2547	593	8396	$\checkmark$	$\otimes$	5
GU–day Mate	Wangzhi Xing	32.9288	26.5547	0.7826	0.2903	2.14	64.2	$\checkmark$	$\otimes$	6

Table 1: Quantitative results of the NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual?Focused Images. The best and second best values per column are highlighted in red and blue , respectively. ”Params.” and ”GFlops” are reported from the teams’ factsheets. A checkmark (

\checkmark

) indicates the use of ensembles or extra data, while a cross (

\otimes

) indicates otherwise.

Figure 1: The pipeline of the method proposed by Team AIIA-Lab

Panel of Figure 2 — Figure 2: Method overview and qualitative results of Team raingod

Figure 3: The pipeline of the method proposed by Team BUU_CV

Figure 4: The pipeline of the method proposed by Team RetinexDualV2

Figure 5: The pipeline of the method proposed by Team ULR

Figure 6: The pipeline of the method proposed by Team GU-day Mate

Figure 7: The pipeline of the method proposed by Team NTR

Figure 8: The pipeline of the method proposed by Team Cidaut AI

Figure 9: The pipeline of the method proposed by Team NUDT–Deeplter

Figure 10: The pipeline of the method proposed by Team DGLTeam

Figure 11: The pipeline of the method proposed by Team MMAIrider

Panel of Figure 12 — Figure 12: The pipeline of the method proposed by Team Rain-SVNIT. The framework consists of a Restormer-based global restoration stage followed by a luminance-based expert routing stage using specialized NAFNet models.

Figure 13: The pipeline of the method proposed by Team Just JiT

Figure 14: The pipeline of the method proposed by Team PSU

Figure 15: The pipeline of the method proposed by Team BITssvgg

Image Deraining

See all 10 papers

OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes
Oct 20, 2025Zhiqiang Teng, Tingting Chen, Beibei Lin +43D Reconstruction Multi-View 3D Reconstruction
Beijing Jiaotong University · National University of Singapore
LoViF 2026 The First Challenge on Unified Removal of Raindrops and Reflections: Methods and Results
Aug 24, 2026Zewei He, Xi Tong, Yu Chen +49Image Enhancement Autonomous Driving Benchmarks
Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
Mar 17, 2026Xingyu Liu, Zewei He, Yu Chen +4Diffusion Models for Image Restoration Image Enhancement
Huanjiang Laboratory, Zhuji, China · School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China · Hangzhou Institute of Technology, Xidian University, Hangzhou, China +1

Oct 20, 2025J/K move · Enter open · S save

OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes

Zhiqiang Teng, Tingting Chen, Beibei Lin, Zifeng Yuan+3

Beijing Jiaotong University · National University of Singapore

3D Reconstruction Multi-View 3D Reconstruction

Open paper AskPDF arXiv

Adherent raindrops on camera lenses are a pervasive source of real-world image degradation, undermining outdoor visual perception for downstream applications such as robotics and 3D scene reconstruction. However, most existing raindrop datasets and methods target only background-focused 2D images, overlooking the equally common raindrop-focused case and the impact of raindrops on 3D scene reconstruction. Moreover, they are almost exclusively daytime, lacking the complex artificial lighting and reflections of nighttime raindrop scenes. To address these issues, we introduce OmniRaindrop, a real-world dataset and benchmark that jointly evaluates 2D raindrop removal and 3D scene reconstruction across raindrop-focused and background-focused captures, under both daytime and nighttime conditions. OmniRaindrop provides spatially aligned raindrop-focused, background-focused, and rain-free ground-truth image sets: a 2D subset of 15,186 aligned pairs/triplets and a 3D subset of 40 real-world scenes evenly split between day and night, totaling 3,822 multi-view images. On top of this data, the benchmark traces how raindrop degradation propagates from 2D restoration to 3D reconstruction by testing representative restoration methods and their effects on pose estimation, point cloud initialization, and 3DGS optimization. Comprehensive experiments reveal that raindrop-focused scenes are substantially harder than background-focused ones, and that errors in 2D restoration and pose/point cloud initialization cascade into degraded 3D reconstruction, pointing to clear directions for more robust 2D restoration and 3DGS design. Building on the dataset, we have organized two consecutive NTIRE challenges (2025 and 2026) on Day and Night Raindrop Removal for Dual-Focused Images.

Abstract

Image Deraining

Explore similar work

OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes

LoViF 2026 The First Challenge on Unified Removal of Raindrops and Reflections: Methods and Results

Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline