Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity

• URL: http://arxiv.org/abs/2211.00837v1
• Date: Wed, 2 Nov 2022 02:47:20 GMT
• Title: Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity
• Authors: Yi Chang, Yun Guo, Yuntong Ye, Changfeng Yu, Lin Zhu, Xile Zhao, Luxin Yan, and Yonghong Tian
• Abstract summary: In this paper, we explore the intrinsic intra-similarity within each layer and inter-exclusiveness between two layers. We propose an unsupervised non-local contrastive learning (NLCL) deraining method.
• Score: 33.188738443097336
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most of the existing learning-based deraining methods are supervisedly trained on synthetic rainy-clean pairs. The domain gap between the synthetic and real rain makes them less generalized to complex real rainy scenes. Moreover, the existing methods mainly utilize the property of the image or rain layers independently, while few of them have considered their mutually exclusive relationship. To solve above dilemma, we explore the intrinsic intra-similarity within each layer and inter-exclusiveness between two layers and propose an unsupervised non-local contrastive learning (NLCL) deraining method. The non-local self-similarity image patches as the positives are tightly pulled together, rain patches as the negatives are remarkably pushed away, and vice versa. On one hand, the intrinsic self-similarity knowledge within positive/negative samples of each layer benefits us to discover more compact representation; on the other hand, the mutually exclusive property between the two layers enriches the discriminative decomposition. Thus, the internal self-similarity within each layer (similarity) and the external exclusive relationship of the two layers (dissimilarity) serving as a generic image prior jointly facilitate us to unsupervisedly differentiate the rain from clean image. We further discover that the intrinsic dimension of the non-local image patches is generally higher than that of the rain patches. This motivates us to design an asymmetric contrastive loss to precisely model the compactness discrepancy of the two layers for better discriminative decomposition. In addition, considering that the existing real rain datasets are of low quality, either small scale or downloaded from the internet, we collect a real large-scale dataset under various rainy kinds of weather that contains high-resolution rainy images.

Related papers

• 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)
• 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)
• Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity [0.0]
  We propose a novel non-local contrastive learning (NLCL) method for unsupervised image deraining. The proposed method obtains state-of-the-art performance in real deraining.
  arXiv  Detail & Related papers  (2022-03-22T07:37:08Z)
• Unpaired Adversarial Learning for Single Image Deraining with Rain-Space Contrastive Constraints [61.40893559933964]
  We develop an effective unpaired SID method which explores mutual properties of the unpaired exemplars by a contrastive learning manner in a GAN framework, named as CDR-GAN. Our method performs favorably against existing unpaired deraining approaches on both synthetic and real-world datasets, even outperforms several fully-supervised or semi-supervised models.
  arXiv  Detail & Related papers  (2021-09-07T10:00:45Z)
• Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation [12.639320247831181]
  We argue that the rain generation and removal are the two sides of the same coin and should be tightly coupled. We propose a bidirectional disentangled translation network, in which each unidirectional network contains two loops of joint rain generation and removal. Experiments on synthetic and real-world rain datasets show the superiority of proposed method compared to state-of-the-arts.
  arXiv  Detail & Related papers  (2021-03-25T08:21:43Z)
• Semi-Supervised Video Deraining with Dynamic Rain Generator [59.71640025072209]
  This paper proposes a new semi-supervised video deraining method, in which a dynamic rain generator is employed to fit the rain layer. Specifically, such dynamic generator consists of one emission model and one transition model to simultaneously encode the spatially physical structure and temporally continuous changes of rain streaks. Various prior formats are designed for the labeled synthetic and unlabeled real data, so as to fully exploit the common knowledge underlying them.
  arXiv  Detail & Related papers  (2021-03-14T14:28:57Z)
• Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal [103.4067418083549]
  We propose a Dual Attention-in-Attention Model (DAiAM) which includes two DAMs for removing both rain streaks and raindrops simultaneously. The proposed method not only is capable of removing rain streaks and raindrops simultaneously, but also achieves the state-of-the-art performance on both tasks.
  arXiv  Detail & Related papers  (2021-03-12T03:00:33Z)
• 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)
• 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)

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.