Single Image Super-Resolution with Arbitrary Magnification Based on High-Frequency Attention Network

Yun, Jun‐Seok; Yoo, Seok Bong

doi:10.3390/math10020275

Cited by 10 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In ( 12 ), mean square error (MSE) is forecasted by ( 13 ) [ 41 ]

SIM ∈ [0, 1]. The higher the score is, the higher the similarity between the restored and original images is.…”

Section: Relevant Theoretical Basis and Experimental Designmentioning

confidence: 99%

Film and Video Quality Optimization Using Attention Mechanism-Embedded Lightweight Neural Network Model

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In filming, the collected video may be blurred due to camera shake and object movement, causing the target edge to be unclear or deforming the targets. In order to solve these problems and deeply optimize the quality of movie videos, this work proposes a video deblurring (VD) algorithm based on neural network (NN) model and attention mechanism (AM). Based on the scale recurrent network, Haar planar wavelet transform (WT) is introduced to preprocess the video image and to deblur the video image in the wavelet domain. Additionally, the spatial and channel AMs are fused into the overall network framework to improve the feature expression ability. Further, the residual inception spatial-channel attention (RISCA) mechanism is introduced to extract the multiscale feature information from video images. Meanwhile, skip spatial-channel attention (SSCA) accelerates the network training time to achieve a better VD effect. Finally, relevant experiments are designed, factoring in peak signal-to-noise ratio (PSNR) and structural similarity (SSI). The experimental findings corroborate that the proposed Haar and attention video deblurring (HAVD) outperforms multisize network Haar (MSNH) in PSNR and structural similarity (SSIM), improved by 0.10 dB and 0.005, respectively. Therefore, embedding the dual AMs can improve the model performance and optimize the video quality. This work provides technical support for solving the video distortion problems.

show abstract

“…In ( 12 ), mean square error (MSE) is forecasted by ( 13 ) [ 41 ]

SIM ∈ [0, 1]. The higher the score is, the higher the similarity between the restored and original images is.…”

Section: Relevant Theoretical Basis and Experimental Designmentioning

confidence: 99%

Film and Video Quality Optimization Using Attention Mechanism-Embedded Lightweight Neural Network Model

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…There have been numerous attempts [36][37][38][39][40][41] to restore images degraded by adverse weather conditions through deep learning. Zamir et al [42] introduced Restormer, an efficient transformer architecture designed for multi-scale local-global representation learning for image restoration tasks.…”

Section: Adverse Weather Restorationmentioning

confidence: 99%

“…Numerous adverse weather restoration models [34][35][36][37][38][39][40][41][42][43][44][45] exist to address these challenges in adverse weather conditions and have demonstrated remarkable performance. However, these models operate independently of detection models, leading to high computational costs and slow inference times.…”

Section: Introductionmentioning

confidence: 99%

Auxcoformer: Auxiliary and Contrastive Transformer for Robust Crack Detection in Adverse Weather Conditions

Yoon,

Jung,

Yoo

2024

Mathematics

Self Cite

View full text Add to dashboard Cite

Crack detection is integral in civil infrastructure maintenance, with automated robots for detailed inspections and repairs becoming increasingly common. Ensuring fast and accurate crack detection for autonomous vehicles is crucial for safe road navigation. In these fields, existing detection models demonstrate impressive performance. However, they are primarily optimized for clear weather and struggle with occlusions and brightness variations in adverse weather conditions. These problems affect automated robots and autonomous vehicle navigation that must operate reliably in diverse environmental conditions. To address this problem, we propose Auxcoformer, designed for robust crack detection in adverse weather conditions. Considering the image degradation caused by adverse weather conditions, Auxcoformer incorporates an auxiliary restoration network. This network efficiently restores damaged crack details, ensuring the primary detection network obtains better quality features. The proposed approach uses a non-local patch-based 3D transform technique, emphasizing the characteristics of cracks and making them more distinguishable. Considering the connectivity of cracks, we also introduce contrastive patch loss for precise localization. Then, we demonstrate the performance of Auxcoformer, comparing it with other detection models through experiments.

show abstract

“…Examples like this prove that an arbitrary-scale SR is essential. Besides CiaoSR [5], pioneering work in arbitrary-scale SR, various methods [6][7][8] have been proposed. However, these methods suffer from long training times because they need to train different scales of LR images and memory problems to generate several LR images.…”

Section: Introductionmentioning

confidence: 99%

Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution

Kim,

Yoo

2023

Mathematics

Self Cite

View full text Add to dashboard Cite

Recently, several arbitrary-scale models have been proposed for single-image super-resolution. Furthermore, the importance of arbitrary-scale single image super-resolution is emphasized for applications such as satellite image processing, HR display, and video-based surveillance. However, the baseline integer-scale model must be retrained to fit the existing network, and the learning speed is slow. This paper proposes a network to solve these problems, processing super-resolution by restoring the high-frequency information lost in the remaining arbitrary-scale while maintaining the baseline integer scale. The proposed network extends an integer-scaled image to an arbitrary-scale target in the discrete cosine transform spectral domain. We also modulate the high-frequency restoration weights of the depthwise multi-head attention to use memory efficiently. Finally, we demonstrate the performance through experiments with existing state-of-the-art models and their flexibility through integration with existing integer-scale models in terms of peak signal-to-noise ratio (PSNR) and similarity index measure (SSIM) scores. This means that the proposed network restores high-resolution (HR) images appropriately by improving the image sharpness of low-resolution (LR) images.

show abstract

Single Image Super-Resolution with Arbitrary Magnification Based on High-Frequency Attention Network

Cited by 10 publications

References 31 publications

Film and Video Quality Optimization Using Attention Mechanism-Embedded Lightweight Neural Network Model

Film and Video Quality Optimization Using Attention Mechanism-Embedded Lightweight Neural Network Model

Auxcoformer: Auxiliary and Contrastive Transformer for Robust Crack Detection in Adverse Weather Conditions

Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution

Contact Info

Product

Resources

About