Attention-Guided Global-Local Adversarial Learning for Detail-Preserving Multi-Exposure Image Fusion

Liu, Jinyuan; Shang, Jingjie; Liu, Risheng; Fan, Xin

doi:10.1109/tcsvt.2022.3144455

Cited by 69 publications

(22 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is the first time that GAN is introduced into MEF. Liu et al [19] presented an attentionguided global-local adversarial learning network to fuse color distortions and enhance details in images. As a secondary, they formulated a novel edge loss function and a spatial feature transform layer to refine the fusion process.…”

Section: B Deep Learning Methodsmentioning

confidence: 99%

“…In the field of MEF, Structure Similarity Index Measure of Multi-exposure Image Fusion (MEF-SSIM) [43] and Peak Signal-to-Noise Ratio (PSNR) are introduced to conduct quantitative analysis, which are commonly used in abundant excellent works, e.g., [19], [47], [48] and [68]. At the same time, we also introduced Mutual Information (MI) [69] and Correlation Coefficient (CC) [70] as supplements.…”

Section: B Evaluation Metricsmentioning

confidence: 99%

“…During the past few decades, a large number of MEF methods have been proposed and applied well. All these methods can be roughly divided into traditional-based frameworks [12], [13], [14], [15] and deep learning-based ones [16], [17], [18], [19], [20]. In traditional methods, feature transformation in the spatial domain [21] and transform domain [22] is a commonly used fusion strategy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

Liu

Zhou

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-refinement in an endto-end manner. Firstly, we obtain shallow feature maps from extreme over/under-exposed source images by a collaborative extraction module. Secondly, smooth attention weight maps are generated under the guidance of a self-attention module, which can draw a global connection to correlate patches in different locations. With the cooperation of the two aforementioned used modules, our proposed network can obtain a coarse fused image. Moreover, by assisting with an edge revision module, edge details of fused results are refined and noise is suppressed effectively. We conduct subjective qualitative and objective quantitative comparisons between the proposed method and twelve state-ofthe-art methods on two available public datasets, respectively. The results show that our fused images significantly outperform others in visual effects and evaluation metrics. In addition, we also perform ablation experiments to verify the function and effectiveness of each module in our proposed method. The source code can be achieved at https://github.com/lok-18/LCNDR.

show abstract

Section: B Deep Learning Methodsmentioning

confidence: 99%

Section: B Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

Liu

Zhou

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…[55] proposed a novel DMEF model and Liu et al. [56] presented an attention‐guided global‐local adversarial learning network. Based on Retinex theory, RetinexNet [57] employed the Enhance‐Net to process the image's illumination map generated by the Decom‐Net.…”

Section: Introductionmentioning

confidence: 99%

“…Ren et al [54] united encoder-decoder with spatially variant recurrent neural network (RNN) to generate visually pleasing images. Relying on the multi-exposure fusion framework, Wu et al [55] proposed a novel DMEF model and Liu et al [56] presented an attention-guided globallocal adversarial learning network. Based on Retinex theory, RetinexNet [57] employed the Enhance-Net to process the image's illumination map generated by the Decom-Net.…”

Section: Introductionmentioning

confidence: 99%

Retinex‐inspired contrast stretch and detail boosting for lowlight image enhancement

Liu

Lan

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Lowlight images with low brightness and contrast, blurry details usually bring us an uncomfortable visual experience. To promote the quality of these deviation images, this paper presents a new and efficient approach, named MFMR, for enhancing lowlight images in the hue‐saturation‐value (HSV) colour space. Concretely, the multi‐angle filter is first applied to estimate the artifact‐free illumination and reflection component of the V‐channel. Afterward, the adaptive bi‐interval histogram with human visual characteristics and morphological operations is employed to process the former, adaptive gamma correction to process the latter for generating various feature maps. In the end, these feature maps are united via adaptive multi‐scale fusion strategy to reconstruct high‐quality images, which are characterized by high contrast and brightness, vivid colour, and clearer details. Extensive experiments show that this method is a well‐proven low‐light image enhancement approach, which outperforms the state‐of‐the‐art comparison methods. Furthermore, the proposed method also can yield satisfying images in the heavy foggy, yellow sand, underwater, and other severe conditions.

show abstract

CFIFusion: Dual‐Branch Complementary Feature Injection Network for Medical Image Fusion

Xie,

Yu,

Ding

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The goal of fusing medical images is to integrate the diverse information that multimodal medical images hold. However, the challenges lie in the limitations of imaging sensors and the issue of incomplete modal information retention, which make it difficult to produce images encompassing both functional and anatomical information. To overcome these obstacles, several medical image fusion techniques based on CNN or transformer architectures have been presented. Nevertheless, CNN technique struggles to establish extensive dependencies between the fused and source images, and transformer architecture often overlooks shallow complementary features. To augment both the feature extraction capacity and the stability of the model, we introduce a framework, called dual‐branch complementary feature injection fusion (CFIFusion) technique, a for multimodal medical image fusion framework that combines unsupervised models of CNN model and transformer techniques. Specifically, in our framework, the entire source image and segmented source image are input into an adaptive backbone network to learn global and local features, respectively. To further retain the source images' complementary information, we design a multi‐scale complementary feature extraction framework as an auxiliary module, focusing on calculating feature differences at each level to capture the shallow complementary information. Then, we design a shallow information preservation module tailored for sliced image characteristics. Experimental results on the Harvard whole brain atlas dataset demonstrate that CFIFusion shows greater benefits than recent state‐of‐the‐art algorithms in terms of both subjective and objective evaluations.

show abstract

Attention-Guided Global-Local Adversarial Learning for Detail-Preserving Multi-Exposure Image Fusion

Cited by 69 publications

References 65 publications

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

Retinex‐inspired contrast stretch and detail boosting for lowlight image enhancement

CFIFusion: Dual‐Branch Complementary Feature Injection Network for Medical Image Fusion

Contact Info

Product

Resources

About