Single Image Rain Streak Removal Using Harris Corner Loss and R-CBAM Network

• URL: http://arxiv.org/abs/2507.23185v1
• Date: Thu, 31 Jul 2025 01:42:12 GMT
• Title: Single Image Rain Streak Removal Using Harris Corner Loss and R-CBAM Network
• Authors: Jongwook Si, Sungyoung Kim,
• Abstract summary: We propose a novel image restoration network that constrains the restoration process by introducing a Corner Loss.<n>We also propose a Residual Convolutional Block Attention Module (R-CBAM) Block into the encoder and decoder to dynamically adjust the importance of features in both spatial and channel dimensions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The problem of single-image rain streak removal goes beyond simple noise suppression, requiring the simultaneous preservation of fine structural details and overall visual quality. In this study, we propose a novel image restoration network that effectively constrains the restoration process by introducing a Corner Loss, which prevents the loss of object boundaries and detailed texture information during restoration. Furthermore, we propose a Residual Convolutional Block Attention Module (R-CBAM) Block into the encoder and decoder to dynamically adjust the importance of features in both spatial and channel dimensions, enabling the network to focus more effectively on regions heavily affected by rain streaks. Quantitative evaluations conducted on the Rain100L and Rain100H datasets demonstrate that the proposed method significantly outperforms previous approaches, achieving a PSNR of 33.29 dB on Rain100L and 26.16 dB on Rain100H.

Related papers

• 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)
• RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering [50.14860376758962]
  We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. Based on the spectral bias property of neural networks, we first optimize the neural rendering pipeline to obtain a low-frequency scene representation. We jointly optimize the two modules, driven by the proposed adaptive direction-sensitive gradient-based reconstruction loss.
  arXiv  Detail & Related papers  (2024-04-17T14:07:22Z)
• 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)
• From heavy rain removal to detail restoration: A faster and better network [26.60300982543502]
  In this work, we introduce a simple dual-stage progressive enhancement network, denoted as DPENet, to achieve effective deraining. This approach comprises two key modules, a rain streaks removal network (R$2$Net) focusing on accurate rain removal, and a details reconstruction network (DRNet) designed to recover the textural details of rain-free images.
  arXiv  Detail & Related papers  (2022-05-07T04:55:05Z)
• Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN [92.15895515035795]
  We describe an approach for supervising deep networks that are based on CycleGAN. We introduce new losses for training CycleGAN that lead to more effective training, resulting in high-quality reconstructions. We demonstrate that the proposed method can be effectively applied to different restoration tasks like de-raining, de-hazing and de-snowing.
  arXiv  Detail & Related papers  (2022-04-23T01:30:47Z)
• Semi-DRDNet Semi-supervised Detail-recovery Image Deraining Network via Unpaired Contrastive Learning [59.22620253308322]
  We propose a semi-supervised detail-recovery image deraining network (termed as Semi-DRDNet) As a semi-supervised learning paradigm, Semi-DRDNet operates smoothly on both synthetic and real-world rainy data in terms of deraining robustness and detail accuracy.
  arXiv  Detail & Related papers  (2022-04-06T12:35:27Z)
• Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing [4.723586858098229]
  ERRA-Net has an impressive speed, processing 1200x1600 HD quality images with an average runtime of 166.11 fps. We use cascaded MA blocks to extract high-frequency features step by step, and the Multi-layer attention fusion tail combines the shallow and deep features of the model to get the residual of the clean image.
  arXiv  Detail & Related papers  (2021-09-12T10:03:44Z)
• Residual Squeeze-and-Excitation Network for Fast Image Deraining [19.48155134126906]
  We propose a residual squeeze-and-excitation network called RSEN for fast image deraining. RSEN adopts a lightweight encoder-decoder architecture to conduct rain removal in one stage.
  arXiv  Detail & Related papers  (2020-06-01T07:17:01Z)
• 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)
• Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline [100.5353614588565]
  We propose to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.
  arXiv  Detail & Related papers  (2020-04-02T17:59:04Z)

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.