UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization

• URL: http://arxiv.org/abs/2603.03967v1
• Date: Wed, 04 Mar 2026 11:58:51 GMT
• Title: UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization
• Authors: Qianfeng Yang, Qiyuan Guan, Xiang Chen, Jiyu Jin, Guiyue Jin, Jiangxin Dong,
• Abstract summary: We propose UniRain, an effective unified image deraining framework capable of restoring images degraded by rain streak and raindrop.<n>To better enhance unified model generalization, we construct an intelligent retrieval augmented generation (RAG)-based dataset distillation pipeline.<n>Our framework performs favorably against the state-of-the-art models on our proposed benchmarks and multiple public datasets.
• Score: 22.057301683465074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite significant progress has been made in image deraining, we note that most existing methods are often developed for only specific types of rain degradation and fail to generalize across diverse real-world rainy scenes. How to effectively model different rain degradations within a universal framework is important for real-world image deraining. In this paper, we propose UniRain, an effective unified image deraining framework capable of restoring images degraded by rain streak and raindrop under both daytime and nighttime conditions. To better enhance unified model generalization, we construct an intelligent retrieval augmented generation (RAG)-based dataset distillation pipeline that selects high-quality training samples from all public deraining datasets for better mixed training. Furthermore, we incorporate a simple yet effective multi-objective reweighted optimization strategy into the asymmetric mixture-of-experts (MoE) architecture to facilitate consistent performance and improve robustness across diverse scenes. Extensive experiments show that our framework performs favorably against the state-of-the-art models on our proposed benchmarks and multiple public datasets.

Related papers

• Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining [73.5575992346396]
  We propose a dual-branch-temporal state-space model to enhance rain streak removal in video sequences.<n>To improve multi-frame feature fusion, we derive a dynamic filter stacking, which adaptively approximates statistical filters for pixel-wise feature refinement.<n>To further explore the capacity of deraining models in supporting other vision-based tasks in rainy environments, we introduce a novel real-world benchmark.
  arXiv  Detail & Related papers  (2025-05-22T15:50:00Z)
• Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining [6.748447305270562]
  We propose a novel Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining framework, CSUD, to tackle the challenges.<n>During training with unpaired data, CSUD is capable of generating high-quality pseudo clean and rainy image pairs.<n>Experiments on multiple synthetic and real-world datasets demonstrate that the deraining performance of CSUD surpasses other state-of-the-art unsupervised methods.
  arXiv  Detail & Related papers  (2025-03-24T14:15:48Z)
• MDeRainNet: An Efficient Macro-pixel Image Rain Removal Network [42.69264615303869]
  We propose an efficient network, called MDeRainNet, for rain streak removal from LF images.<n>The proposed network adopts a multi-scale encoder-decoder architecture, which directly works on Macro-pixel images (MPIs) to improve the rain removal performance.<n>To improve the performance of our network on real-world rainy scenes, we propose a novel semi-supervised learning framework for our MDeRainNet.
  arXiv  Detail & Related papers  (2024-06-15T14:47:02Z)
• Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains [9.6606245317525]
  We develop a Context-based Instance-level Modulation mechanism adept at efficiently modulating CNN- or Transformer-based models. We also devise a rain-/detail-aware contrastive learning strategy to help extract joint rain-/detail-aware representations. By integrating CoI-M with the rain-/detail-aware Contrastive learning, we develop CoIC, an innovative and potent algorithm tailored for training models on mixed datasets.
  arXiv  Detail & Related papers  (2024-04-18T11:20:53Z)
• Contrastive Learning Based Recursive Dynamic Multi-Scale Network for Image Deraining [47.764883957379745]
  Rain streaks significantly decrease the visibility of captured images. Existing deep learning-based image deraining methods employ manually crafted networks and learn a straightforward projection from rainy images to clear images. We propose a contrastive learning-based image deraining method that investigates the correlation between rainy and clear images.
  arXiv  Detail & Related papers  (2023-05-29T13:51:41Z)
• 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)
• A Generic Approach for Enhancing GANs by Regularized Latent Optimization [79.00740660219256]
  We introduce a generic framework called em generative-model inference that is capable of enhancing pre-trained GANs effectively and seamlessly. Our basic idea is to efficiently infer the optimal latent distribution for the given requirements using Wasserstein gradient flow techniques.
  arXiv  Detail & Related papers  (2021-12-07T05:22:50Z)
• From Rain Generation to Rain Removal [67.71728610434698]
  We build a full Bayesian generative model for rainy image where the rain layer is parameterized as a generator. We employ the variational inference framework to approximate the expected statistical distribution of rainy image. Comprehensive experiments substantiate that the proposed model can faithfully extract the complex rain distribution.
  arXiv  Detail & Related papers  (2020-08-08T18:56:51Z)
• Structural Residual Learning for Single Image Rain Removal [48.87977695398587]
  This study proposes a new network architecture by enforcing the output residual of the network possess intrinsic rain structures. Such a structural residual setting guarantees the rain layer extracted by the network finely comply with the prior knowledge of general rain streaks.
  arXiv  Detail & Related papers  (2020-05-19T05:52:13Z)

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.