Unsupervised Image Deraining: Optimization Model Driven Deep CNN

• URL: http://arxiv.org/abs/2203.13699v1
• Date: Fri, 25 Mar 2022 15:13:52 GMT
• Title: Unsupervised Image Deraining: Optimization Model Driven Deep CNN
• Authors: Changfeng Yu, Yi Chang, Yi Li, Xile Zhao, Luxin Yan
• Abstract summary: We propose a unified unsupervised learning framework which inherits the generalization and representation merits for real rain removal. We design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network. The architecture of the network mimics the main role of the optimization models with better feature representation.
• Score: 24.06511813683977
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The deep convolutional neural network has achieved significant progress for single image rain streak removal. However, most of the data-driven learning methods are full-supervised or semi-supervised, unexpectedly suffering from significant performance drops when dealing with real rain. These data-driven learning methods are representative yet generalize poor for real rain. The opposite holds true for the model-driven unsupervised optimization methods. To overcome these problems, we propose a unified unsupervised learning framework which inherits the generalization and representation merits for real rain removal. Specifically, we first discover a simple yet important domain knowledge that directional rain streak is anisotropic while the natural clean image is isotropic, and formulate the structural discrepancy into the energy function of the optimization model. Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization. In addition, the architecture of the network mimics the main role of the optimization models with better feature representation. On one hand, we take advantage of the deep network to improve the representation. On the other hand, we utilize the unsupervised loss of the optimization model for better generalization. Overall, the unsupervised learning framework achieves good generalization and representation: unsupervised training (loss) with only a few real rainy images (input) and physical meaning network (architecture). Extensive experiments on synthetic and real-world rain datasets show the superiority of the proposed method.

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)
• 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)
• 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)
• Removing Rain Streaks via Task Transfer Learning [39.511454098771026]
  We first statistically explore why the supervised deraining models cannot generalize well to real rainy cases. In connected tasks, the label for real data can be easily obtained. Our core idea is to learn representations from real data through task transfer to improve deraining generalization.
  arXiv  Detail & Related papers  (2022-08-28T03:32:17Z)
• RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining [49.99207211126791]
  We specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet) RCDNet embeds the intrinsic priors of rain streaks and has clear interpretability. By end-to-end training such an interpretable network, all involved rain kernels and proximal operators can be automatically extracted.
  arXiv  Detail & Related papers  (2021-07-14T16:08:11Z)
• 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)
• 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)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)

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.