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

Zewei He; Xi Tong; Yu Chen; Xingyu Liu; Xin Li; Zepeng Wang; Jiagao Hu; Fuhao Li

cs.CVAug 24, 2026

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

Authors: Zewei He, Xi Tong, Yu Chen, Xingyu Liu, Xin Li, Zepeng Wang, Jiagao Hu, Fuhao Li, +44 more

Abstract

This workshop paper comprehensively reviews the First Challenge on Unified Removal of Raindrops and Reflections. The challenge aims to address a frequently encountered practical problem in the field of autonomous driving, i.e., raindrop-reflection composite degradation on rainy days. This competition attracted 149 registered participants and received 12 valid final submissions with corresponding fact sheets, significantly contributing to the progress of unified removal of raindrops and reflections. All the methods are developed and evaluated on our real-shot RainDrop and ReFlection (RDRF) dataset. A detailed analysis of the submitted methods and corresponding results is provided in this report, which highlights effective approaches and provides interesting insights for future research.

Figures & tables

Rank	Team	Leader	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Extra Data	Score $\uparrow$
1	X edit M aster	Jiagao Hu	32.3993	0.9645	0.0443	✓	41.8226
2	tysl	Minmin Yi	32.3006	0.9648	0.0416	✓	41.7405
3	GIST-IVL	Yeongjin Jeong	31.6556	0.9680	0.0388	✓	41.1416
4	ACVLAB	Jin-Hui Jiang	31.0060	0.9603	0.0432	✗	40.3933
5	SNU-ISPL	Youngjin Oh	30.7389	0.9572	0.0526	✓	40.0474
6	the_last_token	Vishwajeet Shukla	30.3074	0.9580	0.0559	✓	39.6075

Table 1: Quantitative results on the UR 3 Challenge test set. The bold and underline indicate the best and second-best results.

Rank	Team	Leader	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	Extra Data	Score $\uparrow$
1	X edit M aster	Jiagao Hu	32.3993	0.9645	0.0443	✓	41.8226
2	tysl	Minmin Yi	32.3006	0.9648	0.0416	✓	41.7405
3	ACVLAB	Jin-Hui Jiang	31.0060	0.9603	0.0432	✗	40.3933
4	SNU-ISPL	Youngjin Oh	30.7389	0.9572	0.0526	✓	40.0474
5	GIST-IVL †	Yeongjin Jeong	30.5155	0.9573	0.0516	✓	39.8308
6	the_last_token	Vishwajeet Shukla	30.3074	0.9580	0.0559	✓	39.6075

Table 2: Quantitative results on the UR 3 Challenge test set. The results are obtained with submitted inference codes under strict single-frame setting. The bold and underline indicate the best and second-best results.

Figure 1: The pipeline of the method proposed by Team X edit M aster.

Figure 2: The pipeline of the method proposed by Team tysl.

Figure 3: The overall framework of Team GIST-IVL.

Figure 4: The architecture of Stage III in MAFNet-UR 3 .

Figure 5: The overall framework of Team ACVLAB.

Figure 6: The overall framework of Team SNU-ISPL.

Figure 7: The pipeline of the method proposed by Team the_last_token.

Figure 8: The pipeline of the method proposed by Team AIIA-Lab.

Figure 9: The pipeline of the method proposed by Team ustc_pi_lab.

Explore similar work

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
Learning from synthetic photorealistic raindrop for single image raindrop removal
Sep 29, 2026Zhixiang Hao, Shaodi You, Yu Li +2Synthetic Data Augmentation Physically Based Rendering
State Key Laboratory of VR Technology and Systems, Beihang University, Beijing, China · 61-CSIRO · Tencent +2
EvReflection: Event-Driven Micro-Dynamics for Reflection Removal
Aug 6, 2026Jiaxiao Wang, Dachun Kai, Huyue Zhu +3Image Restoration
University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center

Mar 17, 2026J/K move · Enter open · S save

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

Xingyu Liu, Zewei He, Yu Chen, Chunyu Zhu+3

Huanjiang Laboratory, Zhuji, China · School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China · Hangzhou Institute of Technology, Xidian University, Hangzhou, China+1

Diffusion Models for Image Restoration Image Enhancement All-in-One Image Restoration

Open paper AskPDF arXiv

When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define the unified removal of raindrops and reflections (UR

^3

) task for the first time and construct a real-shot dataset, namely RainDrop and ReFlection (RDRF), which provides a new benchmark with substantial, high-quality, diverse image pairs. Then, we propose a novel diffusion-based framework (i.e., DiffUR

^3

) with several target designs to address this challenging task. By leveraging the powerful generative prior, DiffUR

^3

successfully removes both types of degradations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on our benchmark and on challenging in-the-wild images.

Abstract

Explore similar work

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

Learning from synthetic photorealistic raindrop for single image raindrop removal

EvReflection: Event-Driven Micro-Dynamics for Reflection Removal