Multi-Exposure Image Fusion Techniques: A Comprehensive Review

Xu, Fang; Liu, Jinghong; Song, Yueming; Sun, Hui; Wang, Xuan

doi:10.3390/rs14030771

Cited by 36 publications

(17 citation statements)

References 130 publications

(302 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [32], a comprehensive review of multiexposure image fusion techniques is provided that needs multiple images of different exposure areas and enhanced using different fusion rules. In 2017, the first deep learning-based fusion network called DeepFuse [33], particularly for multiexposure images, was proposed.…”

Section: Fusion-based Methodsmentioning

confidence: 99%

Self-FuseNet: Data Free Unsupervised Remote Sensing Image Super-Resolution

Mishra

Hadar

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Real-world degradations deviate from ideal degradations, as most deep learning-based scenarios involve the ideal synthesis of low-resolution (LR) counterpart images by popularly used bicubic interpolation. Moreover, supervised learning approaches rely on many high-resolution (HR) and LR image pairings to reconstruct missing information based on their association, developed by complex long hours of deep neural network training. Additionally, the trained model's generalizability on various image datasets with various distributions is not guaranteed. To overcome this challenge, we proposed our novel Self-FuseNet, particularly for extremely poor-resolution satellite images. Also, the network exhibits strong generalization performance on additional datasets (both "ideal" and "nonideal" scenarios). The network is especially for those image datasets suffering from the following two significant limitations: 1) nonavailability of ground truth HR images; 2) limitation of a large count of the unpaired dataset for deep neural network training. The benefit of the proposed model is threefold: 1) it does not require any significant extensive training data, either paired or unpaired but only a single LR image without prior knowledge of its distribution; 2) it is a simple and effective model for super-resolving very poor-resolution images, saving computational resources and time; 3) using UNet, the processing of data are accelerated by the network's wide skip connections, allowing image reconstruction with fewer parameters. Rather than using an inverse approach, as common in most deep learning scenarios, we introduced a forward approach to super-resolve exceptionally LR remote sensing images. This demonstrates its supremacy over recently proposed state-of-the-art methods for unsupervised single real-world image blind super-resolution.

show abstract

Section: Fusion-based Methodsmentioning

confidence: 99%

Self-FuseNet: Data Free Unsupervised Remote Sensing Image Super-Resolution

Mishra

Hadar

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The dynamic range of a natural scene is very large, while the dynamic range of a widely used camera is limited and much smaller than the former. One shot imaging of the camera can only acquire a limited interval of the dynamic range of the natural scene, and cannot acquire the whole content of the natural scene completely and truly, resulting in the loss of part of the scene information [1]. To solve this problem, High Dynamic Range (HDR) imaging has been studied.…”

Section: Introductionmentioning

confidence: 99%

“…Multi-exposure image fusion is one of the most widely used methods for high dynamic range image reconstruction, which utilizes a series of input images with different exposure levels to directly generate highquality images with rich details that match the perceptual characteristics of the human eye. The fusion process eliminates the need for steps such as estimating the camera response function, HDR image reconstruction, and tone mapping, and the algorithm is simple, efficient, and easy to implement [1,2].…”

Section: Introductionmentioning

confidence: 99%

A multi-exposure image fusion method based on histogram matching and convolutional neural network

Zhu,

Zhang,

Fang

et al. 2024

International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023)

View full text Add to dashboard Cite

For high dynamic range image reconstruction in dynamic scenes, this paper proposes a multi-exposure sequence image fusion method based on histogram matching and convolutional neural network. First, image alignment is performed on the reference image based on the histogram matching method. Then, a multi-exposure fusion model based on convolutional neural network is constructed for the aligned multi-exposure sequence images. Finally, the fusion model is trained based on the training data, and the multi-exposure sequence image fusion in dynamic scenes is realized. The experimental results show that the method proposed in this chapter effectively avoids the influence of dynamic scenes on the fusion of multi-exposure sequence images, and at the same time can generate high-quality fused images.

show abstract

“…Because of the time difference in the image acquisition, the position and shape of the moving objects are variable in the image sequence with different exposures. If these images are fused directly, some issues, such as blur, ghosts, and translucent areas, may appear in the fused result, 4 , 5 which will seriously affect the visual quality of the fused image, as shown in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

Multi-exposure image fusion of dynamic scenes using consistency detection and weighted least squares filtering

Liu

Wang

et al. 2023

Opt. Eng.

Self Cite

View full text Add to dashboard Cite

.The high dynamic range image obtained by multi-exposure image fusion (MEF) contains more detailed information, which has broad application prospects and crucial practical significance in many fields. However, due to the introduction of the ghosting artifacts caused by object movement and camera shake, MEF in the dynamic scenes has always been a challenge. To address this problem, we designed a deghosting method for MEF. The over- and under-exposed images are corrected by intensity mapping and consistency detection to obtain the aligned latent images. Then the high- and low-frequency components of the latent images are generated using weighted least squares filtering. The blending weights are calculated based on the image luminance and the exposedness function. These frequency components are integrated into the final deghosted image with more texture details and vivid color. A comprehensive evaluation experiment is carried out, proving that the proposed method has a better visual effect and stable performance than the state-of-the-art deghosting MEF methods.

show abstract

Multi-Exposure Image Fusion Techniques: A Comprehensive Review

Cited by 36 publications

References 130 publications

Self-FuseNet: Data Free Unsupervised Remote Sensing Image Super-Resolution

Self-FuseNet: Data Free Unsupervised Remote Sensing Image Super-Resolution

A multi-exposure image fusion method based on histogram matching and convolutional neural network

Multi-exposure image fusion of dynamic scenes using consistency detection and weighted least squares filtering

Contact Info

Product

Resources

About