MCW-Net: Single Image Deraining with Multi-level Connections and Wide Regional Non-local Blocks

• URL: http://arxiv.org/abs/2009.13990v4
• Date: Sun, 3 Apr 2022 10:40:38 GMT
• Title: MCW-Net: Single Image Deraining with Multi-level Connections and Wide Regional Non-local Blocks
• Authors: Yeachan Park, Myeongho Jeon, Junho Lee and Myungjoo Kang
• Abstract summary: We present a multi-level connection and wide regional non-local block network (MCW-Net) to restore the original background textures in rainy images. MCW-Net improves performance by maximizing information utilization without additional branches. Experimental results on both synthetic and real-world rainy datasets demonstrate that the proposed model significantly outperforms existing state-of-the-art models.
• Score: 6.007222067550804
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A recent line of convolutional neural network-based works has succeeded in capturing rain streaks. However, difficulties in detailed recovery still remain. In this paper, we present a multi-level connection and wide regional non-local block network (MCW-Net) to properly restore the original background textures in rainy images. Unlike existing encoder-decoder-based image deraining models that improve performance with additional branches, MCW-Net improves performance by maximizing information utilization without additional branches through the following two proposed methods. The first method is a multi-level connection that repeatedly connects multi-level features of the encoder network to the decoder network. Multi-level connection encourages the decoding process to use the feature information of all levels. In multi-level connection, channel-wise attention is considered to learn which level of features is important in the decoding process of the current level. The second method is a wide regional non-local block. As rain streaks primarily exhibit a vertical distribution, we divide the grid of the image into horizontally-wide patches and apply a non-local operation to each region to explore the rich rain-free background information. Experimental results on both synthetic and real-world rainy datasets demonstrate that the proposed model significantly outperforms existing state-of-the-art models. Furthermore, the results of the joint deraining and segmentation experiment prove that our model contributes effectively to other vision tasks.

Related papers

• 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)
• Dual Residual Attention Network for Image Denoising [19.978731146465822]
  In image denoising, deep convolutional neural networks (CNNs) can obtain favorable performance on removing spatially invariant noise. We propose a novel Dual-branch Residual Attention Network (DRANet) for image denoising. Our DRANet can produce competitive denoising performance both on synthetic and real-world noise removal.
  arXiv  Detail & Related papers  (2023-05-07T13:11:55Z)
• Online-updated High-order Collaborative Networks for Single Image Deraining [51.22694467126883]
  Single image deraining is an important task for some downstream artificial intelligence applications such as video surveillance and self-driving systems. We propose a high-order collaborative network with multi-scale compact constraints and a bidirectional scale-content similarity mining module. Our proposed method performs favorably against eleven state-of-the-art methods on five public synthetic and one real-world dataset.
  arXiv  Detail & Related papers  (2022-02-14T09:09:08Z)
• Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining [8.964751500091005]
  Rain streaks bring serious blurring and visual quality degradation, which often vary in size, direction and density. Current CNN-based methods achieve encouraging performance, while are limited to depict rain characteristics and recover image details in the poor visibility environment. We present a Multi-scale Hourglass Hierarchical Fusion Network (MH2F-Net) in end-to-end manner, to exactly captures rain streak features with multi-scale extraction, hierarchical distillation and information aggregation.
  arXiv  Detail & Related papers  (2021-04-25T08:27:01Z)
• Multi-Stage Progressive Image Restoration [167.6852235432918]
  We propose a novel synergistic design that can optimally balance these competing goals. Our main proposal is a multi-stage architecture, that progressively learns restoration functions for the degraded inputs. The resulting tightly interlinked multi-stage architecture, named as MPRNet, delivers strong performance gains on ten datasets.
  arXiv  Detail & Related papers  (2021-02-04T18:57:07Z)
• Exploring Overcomplete Representations for Single Image Deraining using CNNs [0.0]
  Most recent methods for deraining use a deep network which captures low-level features across the initial layers and high-level features in the deeper layers. We propose using an overcomplete convolutional network architecture which gives special attention in learning local structures. We combine it with U-Net so that it does not lose out on the global structures as well while focusing more on low-level features.
  arXiv  Detail & Related papers  (2020-10-20T22:55:02Z)
• DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal [13.794959799789703]
  Rain removal is an important but challenging computer vision task as rain streaks can severely degrade the visibility of images. Previous works mainly focused on feature extraction and processing or neural network structure. In this paper, we explore the cross-scale manner between networks and inner-scale fusion operation to solve the image rain removal task.
  arXiv  Detail & Related papers  (2020-08-03T10:34:45Z)
• A Model-driven Deep Neural Network for Single Image Rain Removal [52.787356046951494]
  We propose a model-driven deep neural network for the task, with fully interpretable network structures. Based on the convolutional dictionary learning mechanism for representing rain, we propose a novel single image deraining model. All the rain kernels and operators can be automatically extracted, faithfully characterizing the features of both rain and clean background layers.
  arXiv  Detail & Related papers  (2020-05-04T09:13:25Z)
• Multi-Scale Progressive Fusion Network for Single Image Deraining [84.0466298828417]
  Rain streaks in the air appear in various blurring degrees and resolutions due to different distances from their positions to the camera. Similar rain patterns are visible in a rain image as well as its multi-scale (or multi-resolution) versions. In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features.
  arXiv  Detail & Related papers  (2020-03-24T17:22:37Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.