Exploiting Regional Information Transformer for Single Image Deraining

• URL: http://arxiv.org/abs/2402.16033v2
• Date: Sun, 4 Aug 2024 17:37:02 GMT
• Title: Exploiting Regional Information Transformer for Single Image Deraining
• Authors: Baiang Li, Zhao Zhang, Huan Zheng, Xiaogang Xu, Yanyan Wei, Jingyi Zhang, Jicong Fan, Meng Wang,
• Abstract summary: Region Transformer Block (RTB) integrates a Region Masked Attention (RMA) mechanism and a Mixed Gate Forward Block (MGFB) Our model reaches state-of-the-art performance, significantly improving the image deraining quality.
• Score: 40.96287901893822
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Transformer-based Single Image Deraining (SID) methods have achieved remarkable success, primarily attributed to their robust capability in capturing long-range interactions. However, we've noticed that current methods handle rain-affected and unaffected regions concurrently, overlooking the disparities between these areas, resulting in confusion between rain streaks and background parts, and inabilities to obtain effective interactions, ultimately resulting in suboptimal deraining outcomes. To address the above issue, we introduce the Region Transformer (Regformer), a novel SID method that underlines the importance of independently processing rain-affected and unaffected regions while considering their combined impact for high-quality image reconstruction. The crux of our method is the innovative Region Transformer Block (RTB), which integrates a Region Masked Attention (RMA) mechanism and a Mixed Gate Forward Block (MGFB). Our RTB is used for attention selection of rain-affected and unaffected regions and local modeling of mixed scales. The RMA generates attention maps tailored to these two regions and their interactions, enabling our model to capture comprehensive features essential for rain removal. To better recover high-frequency textures and capture more local details, we develop the MGFB as a compensation module to complete local mixed scale modeling. Extensive experiments demonstrate that our model reaches state-of-the-art performance, significantly improving the image deraining quality. Our code and trained models are publicly available.

Related papers

• Region Attention Transformer for Medical Image Restoration [16.33261165253018]
  We introduce a novel Region Attention Transformer (RAT) that utilizes a region-based multi-head self-attention mechanism (R-MSA) RAT partitions the input image into non-overlapping semantic regions using the robust Segment Anything Model (SAM) This region is more flexible and interpretable, ensuring that only pixels from similar semantic regions complement each other, eliminating interference from irrelevant regions. Experiments demonstrate the effectiveness of RAT in various medical image restoration tasks, including PET image synthesis, CT image denoising, and pathological image super-resolution.
  arXiv  Detail & Related papers  (2024-07-12T13:52:05Z)
• Coherent and Multi-modality Image Inpainting via Latent Space Optimization [61.99406669027195]
  PILOT (intextbfPainting vtextbfIa textbfLatent textbfOptextbfTimization) is an optimization approach grounded on a novel textitsemantic centralization and textitbackground preservation loss. Our method searches latent spaces capable of generating inpainted regions that exhibit high fidelity to user-provided prompts while maintaining coherence with the background.
  arXiv  Detail & Related papers  (2024-07-10T19:58:04Z)
• Image Deraining with Frequency-Enhanced State Space Model [2.9465623430708905]
  This study introduces SSM to image deraining with deraining-specific enhancements and proposes a Deraining Frequency-Enhanced State Space Model (DFSSM) We develop a novel mixed-scale gated-convolutional block, which uses convolutions with multiple kernel sizes to capture various scale degradations effectively. Experiments on synthetic and real-world rainy image datasets show that our method surpasses state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-26T07:45:12Z)
• Look-Around Before You Leap: High-Frequency Injected Transformer for Image Restoration [46.96362010335177]
  In this paper, we propose HIT, a simple yet effective High-frequency Injected Transformer for image restoration. Specifically, we design a window-wise injection module (WIM), which incorporates abundant high-frequency details into the feature map, to provide reliable references for restoring high-quality images. In addition, we introduce a spatial enhancement unit (SEU) to preserve essential spatial relationships that may be lost due to the computations carried out across channel dimensions in the BIM.
  arXiv  Detail & Related papers  (2024-03-30T08:05:00Z)
• Gabor-guided transformer for single image deraining [2.330361251490783]
  We propose a Gabor-guided tranformer (Gabformer) for single image deraining. The focus on local texture features is enhanced by incorporating the information processed by the Gabor filter into the query vector. Our method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-03-12T07:41:51Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• Magic ELF: Image Deraining Meets Association Learning and Transformer [63.761812092934576]
  This paper aims to unify CNN and Transformer to take advantage of their learning merits for image deraining. A novel multi-input attention module (MAM) is proposed to associate rain removal and background recovery. Our proposed method (dubbed as ELF) outperforms the state-of-the-art approach (MPRNet) by 0.25 dB on average.
  arXiv  Detail & Related papers  (2022-07-21T12:50:54Z)
• 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.