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

• URL: http://arxiv.org/abs/2603.16446v1
• Date: Tue, 17 Mar 2026 12:30:14 GMT
• Title: Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
• Abstract summary: raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images.<n>We first formally define the unified removal of raindrops and reflections (UR$3$) task for the first time.<n>We propose a novel diffusion-based framework (i.e., DiffUR$3$) with several target designs to address this challenging task.
• Score: 23.05612697278085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. The RDRF dataset and the codes will be made public upon acceptance.

Related papers

• Unsupervised Raindrop Removal from a Single Image using Conditional Diffusion Models [0.0]
  Raindrop removal from a single image is a challenging task in image processing.<n>Recent advances in the use of diffusion models have led to state-of-the-art image inpainting techniques.<n>We introduce a novel technique for raindrop removal from a single image using diffusion-based image inpainting.
  arXiv  Detail & Related papers  (2025-05-13T03:00:01Z)
• NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results [173.5963741512905]
  This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images.<n>This challenge received a wide range of impressive solutions, which are developed and evaluated using our collected real-world Raindrop Clarity dataset.<n>The primary objective of this challenge is to establish a new and powerful benchmark for the task of removing raindrops under varying lighting and focus conditions.
  arXiv  Detail & Related papers  (2025-04-17T07:35:35Z)
• Unsupervised Network for Single Image Raindrop Removal [4.982370044801629]
  This study proposes a deep neural network for raindrop removal based on unsupervised learning.<n>Our proposed model performs layer separation based on cycle network architecture.<n>Experiments on raindrop benchmark datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-12-04T04:10:50Z)
• Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks [17.00078021737863]
  In the real world, image degradations caused by rain often exhibit a combination of rain streaks and raindrops, thereby increasing the challenges of recovering the underlying clean image. This paper aims to present an efficient and flexible mechanism to learn and model degradation relationships in a global view.
  arXiv  Detail & Related papers  (2023-08-27T16:33:11Z)
• From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal [28.029107707930063]
  We construct a Large-scale High-quality Paired real rain benchmark (LHP-Rain), including 3000 video sequences with 1 million high-resolution (1920*1080) frame pairs. The advantages of the proposed dataset are three-fold: rain with higher-diversity and larger-scale, image with higher-resolution and higher-quality ground-truth.
  arXiv  Detail & Related papers  (2023-08-07T18:39:14Z)
• Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark [57.85378202032541]
  Rain in the dark poses a significant challenge to deploying real-world applications such as autonomous driving, surveillance systems, and night photography. Existing low-light enhancement or deraining methods struggle to brighten low-light conditions and remove rain simultaneously. We introduce an end-to-end model called L$2$RIRNet, designed to manage both low-light enhancement and deraining in real-world settings.
  arXiv  Detail & Related papers  (2023-05-06T10:17:42Z)
• Rethinking Real-world Image Deraining via An Unpaired Degradation-Conditioned Diffusion Model [51.49854435403139]
  We propose RainDiff, the first real-world image deraining paradigm based on diffusion models. We introduce a stable and non-adversarial unpaired cycle-consistent architecture that can be trained, end-to-end, with only unpaired data for supervision. We also propose a degradation-conditioned diffusion model that refines the desired output via a diffusive generative process conditioned by learned priors of multiple rain degradations.
  arXiv  Detail & Related papers  (2023-01-23T13:34:01Z)
• Toward Real-world Single Image Deraining: A New Benchmark and Beyond [79.5893880599847]
  Single image deraining (SID) in real scenarios attracts increasing attention in recent years. Previous real datasets suffer from low-resolution images, homogeneous rain streaks, limited background variation, and even misalignment of image pairs. We establish a new high-quality dataset named RealRain-1k, consisting of $1,120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively.
  arXiv  Detail & Related papers  (2022-06-11T12:26:59Z)
• Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior [103.49307603952144]
  Most existing de-rain algorithms use only one single input image and aim to recover a clean image. We present a Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information. Experiments on both monocular and the newly proposed stereo rainy datasets demonstrate that the proposed method achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-05-09T04:15:10Z)
• Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance [78.34235841168031]
  We present a novel two-stage network with reflection-aware guidance (RAGNet) for single image reflection removal (SIRR) RAG can be used (i) to mitigate the effect of reflection from the observation, and (ii) to generate mask in partial convolution for mitigating the effect of deviating from linear combination hypothesis. Experiments on five commonly used datasets demonstrate the quantitative and qualitative superiority of our RAGNet in comparison to the state-of-the-art SIRR methods.
  arXiv  Detail & Related papers  (2020-12-02T03:14:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.