Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis

Zhang, Kai; Li, Yawei; Liang, Jingyun; Cao, Jiezhang; Zhang, Yulun; Tang, Hao; Timofte, Radu; Gool, Luc Van

doi:10.48550/arxiv.2203.13278

Cited by 17 publications

(28 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in the comparative study in [19], the U-Net architecture as proposed in [37] has the best overall performance compared to several other architectures without skipped connections. Several recent works on image denoising also demonstrate a good performance of U-Net denoising [38].…”

Section: Related Workmentioning

confidence: 72%

Robust Time Series Denoising with Learnable Wavelet Packet Transform

Frusque¹,

Fink²

2022

Preprint

View full text Add to dashboard Cite

In many applications, signal denoising is often the first pre-processing step before any subsequent analysis or learning task. In this paper, we propose to apply a deep learning denoising model inspired by a signal processing, a learnable version of wavelet packet transform. The proposed algorithm has signficant learning capabilities with few interpretable parameters and has an intuitive initialisation. We propose a post-learning modification of the parameters to adapt the denoising to different noise levels. We evaluate the performance of the proposed methodology on two case studies and compare it to other state of the art approaches, including wavelet schrinkage denoising, convolutional neural network, autoencoder and U-net deep models. The first case study is based on designed functions that have typically been used to study denoising properties of the algorithms. The second case study is an audio background removal task. We demonstrate how the proposed algorithm relates to the universality of signal processing methods and the learning capabilities of deep learning approaches. In particular, we evaluate the obtained denoising performances on structured noisy signals inside and outside the classes used for training. In addition to having good performance in denoising signals inside and outside to the training class, our method shows to be particularly robust when different noise levels, noise types and artifacts are added.

show abstract

Section: Related Workmentioning

confidence: 72%

Robust Time Series Denoising with Learnable Wavelet Packet Transform

Frusque¹,

Fink²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…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%

“…There is a recent work on SCUNet [18], a U-Net based on Swin Transformer, for a blind denoising. The basic module SC block of SCUNet combines the Swin Transformer and residual convolutional block.…”

Section: Introduction and Related Workmentioning

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

“…Although the model proposed in this paper has some similarities with the model proposed in [ 29 ], there are still large differences between them. In [ 29 ], after

-sized convolution, it is divided into two parts whose channel number is half of the input channel number.…”

Section: Proposed Transformer–convolution Fusion Dehazing Networkmentioning

confidence: 96%

“…The authors in [ 29 ] proposed a similar structure for image denoising tasks to integrate the feature extraction and reconstruction capabilities of Transformer and convolution. Its model structure is shown in Figure 3 .…”

Section: Proposed Transformer–convolution Fusion Dehazing Networkmentioning

confidence: 99%

An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network

Xu¹,

Chen

Luo

et al. 2022

Sensors

View full text Add to dashboard Cite

The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer’s global modeling ability and convolutional neural network’s local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends.

show abstract

Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis

Cited by 17 publications

References 46 publications

Robust Time Series Denoising with Learnable Wavelet Packet Transform

Robust Time Series Denoising with Learnable Wavelet Packet Transform

Residual Swin Transformer Channel Attention Network for Image Demosaicing

An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network

Contact Info

Product

Resources

About