Dilated Convolutional Transformer for High-Quality Image Deraining

Li, Yufeng; Lu, Jiyang; Chen, Hongming; Wu, Xianhao; Chen, Xiang

doi:10.1109/cvprw59228.2023.00442

Cited by 14 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, the proposed algorithm is compared with other popular deraining algorithms, including JORDER‐E [17], Rescan [18], PreNet [19], BRN [20], MPRNet [21], KDRN [22], PDFN [23], Nc‐derain [24], IDT [25], DRAN [26], and DCT [27]. For fair comparison, the comparison algorithms and the proposed algorithm are both based on deep learning methods.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Single‐image deraining algorithm based on multi‐stage recurrent network

Li,

Guo

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

The damage caused by the rain streak attached to the rainy image to the background seriously affects the analysis of image information and subsequent research. Aiming at the problem that the current single image rain removal methods cannot extract the deep rain streak features, a single image deraining algorithm based on multi‐stage recurrent network is proposed, which is committed to separating the rain streak layer and the background layer. The network consists of three stages, each stage is mainly composed of upper and lower scale dilation blocks, the upper scale dilation block includes multi‐scale dilated convolution and scale fusion, the lower scale dilation block is set the same, and the stages are connected using improved gated recurrent units to facilitate parameter sharing between them. The experimental results show that the proposed algorithm outperforms the comparative algorithm in both quantitative indicators and qualitative analysis on synthetic and real datasets, and the restored image retains more detailed information.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Li et al. [27] proposed a network that combines dilated convolution and transformer to expand the receptive field of the convolution kernel through dilated convolution. The Transformer is used to learn global dependencies to better reconstruct and remove raindrop traces.…”

Section: Introductionmentioning

confidence: 99%

Single‐image deraining algorithm based on multi‐stage recurrent network

Li,

Guo

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…During the stage of high-resolution image restoration, this paper incorporates a prompting module into the framework to generate prompts and enrich input features for dynamically guiding the restoration process of the restoration module. This paper also introduces skip connections (Li et al, 2023a) to bridge consecutive intermediate features, ensuring stable training. Next, this paper provides a detailed description of the proposed restoration module, prompting module, and their core building blocks.…”

Section: Overall Pipelinementioning

confidence: 99%

Learning degradation-aware visual prompt for maritime image restoration under adverse weather conditions

He,

Jia,

2024

Front. Mar. Sci.

View full text Add to dashboard Cite

Adverse weather conditions such as rain and haze often lead to a degradation in the quality of maritime images, which is crucial for activities like navigation, fishing, and search and rescue. Therefore, it is of great interest to develop an effective algorithm to recover high-quality maritime images under adverse weather conditions. This paper proposes a prompt-based learning method with degradation perception for maritime image restoration, which contains two key components: a restoration module and a prompting module. The former is employed for image restoration, whereas the latter encodes weather-related degradation-specific information to modulate the restoration module, enhancing the recovery process for improved results. Inspired by the recent trend of prompt learning in artificial intelligence, this paper adopts soft-prompt technology to generate learnable visual prompt parameters for better perceiving the degradation-conditioned cues. Extensive experimental results on several benchmarks show that our approach achieves superior restoration performance in maritime image dehazing and deraining tasks.

show abstract

“…We calculate the PSNR and SSIM along the Y channel in the YCbCr color space as quantitative comparisons. We compare our method with 14 image deraining approaches, including Derain-Net [13], SEMI [44], DIDMDN [51], UMRL [48], RESCAN [28], PReNet [37], MSPFN [24], MPRNet [49], KiT [25], DGUNet [33], IDT [46], HINet [6], DCT [29] and SFNet [8]. In Tab.…”

Section: Other Taskmentioning

confidence: 99%

A Novel U-Shaped Hybrid Network for Single Image Dehazing

Zhang,

2023

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)

View full text Add to dashboard Cite

Currently, Transformer is the most popular architecture for image dehazing, but due to its large computational complexity, its ability to handle long-range dependency is limited on resource-constrained devices. To tackle this challenge, we introduce the U-shaped Vision Mamba (UVM-Net), an efficient single-image dehazing network. Inspired by the State Space Sequence Models (SSMs), a new deep sequence model known for its power to handle long sequences, we design a Bi-SSM block that integrates the local feature extraction ability of the convolutional layer with the ability of the SSM to capture long-range dependencies. Extensive experimental results demonstrate the effectiveness of our method.Our method provides a more highly efficient idea of long-range dependency modeling for image dehazing as well as other image restoration tasks. The URL of the code is https://github.com/zzr-idam.

show abstract

Dilated Convolutional Transformer for High-Quality Image Deraining

Cited by 14 publications

References 34 publications

Single‐image deraining algorithm based on multi‐stage recurrent network

Single‐image deraining algorithm based on multi‐stage recurrent network

Learning degradation-aware visual prompt for maritime image restoration under adverse weather conditions

A Novel U-Shaped Hybrid Network for Single Image Dehazing

Contact Info

Product

Resources

About