SUNet: Swin Transformer UNet for Image Denoising

Fan, Chi-Mao; Liu, Tsung-Jung; Liu, Kuan-Hsien

doi:10.48550/arxiv.2202.14009

Cited by 8 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The U-Net architecture is very popular in image restoration networks. One may expect that a combination of Swin Transformer and U-Net can further improve the performance of model [15,18,27]. We have trained a model with U-Net structure, denoted as RSTCAUNet.…”

Section: A Ablation Study and Discussionmentioning

confidence: 99%

Residual Swin Transformer Channel Attention Network for Image Demosaicing

Xing¹,

Егиазарян²

2022

Preprint

View full text Add to dashboard Cite

Image demosaicing is problem of interpolating fullresolution color images from raw sensor (color filter array) data. During last decade, deep neural networks have been widely used in image restoration, and in particular, in demosaicing, attaining significant performance improvement. In recent years, vision transformers have been designed and successfully used in various computer vision applications. One of the recent methods of image restoration based on a Swin Transformer (ST), SwinIR, demonstrates state-of-the-art performance with a smaller number of parameters than neural network-based methods. Inspired by the success of SwinIR, we propose in this paper a novel Swin Transformer-based network for image demosaicing, called RSTCANet. To extract image features, RSTCANet stacks several residual Swin Transformer Channel Attention blocks (RSTCAB), introducing the channel attention for each two successive ST blocks. Extensive experiments demonstrate that RSTCANet outperforms state-of-the-art image demosaicing methods, and has a smaller number of parameters.

show abstract

Section: A Ablation Study and Discussionmentioning

confidence: 99%

Residual Swin Transformer Channel Attention Network for Image Demosaicing

Xing¹,

Егиазарян²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…SwinIR [32] employed ST as the backbone and achieved the best performance in the field. Fan et al [33] proposed a restoration model called SUNet, which uses the ST layer as our basic block and then is applied to UNet architecture for image denoising. We also use the ST layer to build the transformer branch in our model.…”

Section: Vision Transformermentioning

confidence: 99%

A joint image super‐resolution network for multiple degradations removal via complementary transformer and convolutional neural network

Li,

Zhou,

Wang

2024

IET Image Processing

View full text Add to dashboard Cite

While recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) and vision transformers in single‐image super‐resolution (SISR), the degradation assumptions are simple and usually bicubic downsampling. Thus, their performances will drop dramatically when the actual degradation does not match this assumption, and they lack the capability to handle multiple degradations (e.g. Gaussian noise, bicubic downsizing, and salt & pepper noise). To address the issues, in this paper, the authors propose a joint SR model (JIRSR) that can effectively handle multiple degradations in a single model. Specifically, the authors build the parallel Transformer and CNN branches that complement each other through bidirectional feature fusion. Moreover, the authors also adopt a random permutation of different kinds of noise and resizing operations to build the training datasets. Extensive experiments on classical SR, denoising, and multiple degradation removal demonstrate that the authors’ JIRSR achieves state‐of‐the‐art (SOTA) performance on public benchmarks. Concretely, the authors’ JIRSR outperforms the second‐best model by 0.23 to 0.74 dB for multiple degradations removal and is 0.20 to 0.36 dB higher than the SOTA methods on the Urban100 dataset under the ×4 SR task.

show abstract

“…In [96], the authors combined UNet [97] and Swin transformer [19] to propose SUNet for image denoising. The model was evaluated on CBSD68 [98] and Kodak24 [99] dataset.…”

Section: Vits For Image Denoisingmentioning

confidence: 99%

A Comprehensive Survey of Transformers for Computer Vision

Jamil

Piran

Kwon

2023

Drones

View full text Add to dashboard Cite

As a special type of transformer, vision transformers (ViTs) can be used for various computer vision (CV) applications. Convolutional neural networks (CNNs) have several potential problems that can be resolved with ViTs. For image coding tasks such as compression, super-resolution, segmentation, and denoising, different variants of ViTs are used. In our survey, we determined the many CV applications to which ViTs are applicable. CV applications reviewed included image classification, object detection, image segmentation, image compression, image super-resolution, image denoising, anomaly detection, and drone imagery. We reviewed the state of the-art and compiled a list of available models and discussed the pros and cons of each model.

show abstract

SUNet: Swin Transformer UNet for Image Denoising

Cited by 8 publications

References 37 publications

Residual Swin Transformer Channel Attention Network for Image Demosaicing

Residual Swin Transformer Channel Attention Network for Image Demosaicing

A joint image super‐resolution network for multiple degradations removal via complementary transformer and convolutional neural network

A Comprehensive Survey of Transformers for Computer Vision

Contact Info

Product

Resources

About