Gradient field multi-exposure images fusion for high dynamic range image visualization

Gu, Bo; Li, Wujing; Wong, Jiangtao; Zhu, Minyun; Wang, Minghui

doi:10.1016/j.jvcir.2012.02.009

Cited by 122 publications

(85 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The adoption of gradient direction enables the method to fuse a source sequence captured in a dynamic scene that has moving objects. A similar gradient-based MEF method is proposed in [9]. Based on [5], Li et al [10] enhanced the details of a given fused image by solving a quadratic optimization problem.…”

Section: Related Workmentioning

confidence: 99%

“…Eight MEF algorithms are selected, which include simple operators such as 1) local energy weighted linear combination and 2) global energy weighted linear combination, as well as advanced MEF algorithms such as 3) Raman09 [6], 4) Gu12 [9], 5) ShutaoLi12 [11], 6) ShutaoLi13 [12], 7) Li12 [10], and 8) Mertens07 [5]. These algorithms are chosen to cover a diverse types of MEF methods in terms of methodology and behavior.…”

Section: A Image Database and Subjective User Studymentioning

confidence: 99%

See 1 more Smart Citation

Perceptual Quality Assessment for Multi-Exposure Image Fusion

Zeng

Wang

2015

IEEE Trans. on Image Process.

819

348

View full text Add to dashboard Cite

Multi-exposure image fusion (MEF) is considered an effective quality enhancement technique widely adopted in consumer electronics, but little work has been dedicated to the perceptual quality assessment of multi-exposure fused images. In this paper, we first build an MEF database and carry out a subjective user study to evaluate the quality of images generated by different MEF algorithms. There are several useful findings. First, considerable agreement has been observed among human subjects on the quality of MEF images. Second, no single state-of-the-art MEF algorithm produces the best quality for all test images. Third, the existing objective quality models for general image fusion are very limited in predicting perceived quality of MEF images. Motivated by the lack of appropriate objective models, we propose a novel objective image quality assessment (IQA) algorithm for MEF images based on the principle of the structural similarity approach and a novel measure of patch structural consistency. Our experimental results on the subjective database show that the proposed model well correlates with subjective judgments and significantly outperforms the existing IQA models for general image fusion. Finally, we demonstrate the potential application of the proposed model by automatically tuning the parameters of MEF algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A Image Database and Subjective User Studymentioning

confidence: 99%

Perceptual Quality Assessment for Multi-Exposure Image Fusion

Zeng

Wang

2015

IEEE Trans. on Image Process.

819

348

View full text Add to dashboard Cite

show abstract

“…Because a block may span different objects, this approach cannot handle object boundaries. Gu et al [6] proposed a gradient field multi-exposure image fusion method for HDR image visualization. The advantage of this method is its computational efficiency and robustness.…”

Section: Related Workmentioning

confidence: 99%

End-to-End Exposure Fusion Using Convolutional Neural Network

Wang

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we describe the direct learning of an end-toend mapping between under-/over-exposed images and well-exposed images. The mapping is represented as a deep convolutional neural network (CNN) that takes multiple-exposure images as input and outputs a highquality image. Our CNN has a lightweight structure, yet gives state-ofthe-art fusion quality. Furthermore, we know that for a given pixel, the influence of the surrounding pixels gradually increases as the distance decreases. If the only pixels considered are those in the convolution kernel neighborhood, the final result will be affected. To overcome this problem, the size of the convolution kernel is often increased. However, this also increases the complexity of the network (too many parameters) and the training time. In this paper, we present a method in which a number of sub-images of the source image are obtained using the same CNN model, providing more neighborhood information for the convolution operation. Experimental results demonstrate that the proposed method achieves better performance in terms of both objective evaluation and visual quality. key words: exposure fusion, convolutional neural networks, fusion rule, activity level measurement

show abstract

“…This algorithm, based on the Retinex theory of vision, is specifically designed to prevent the formation of common artifacts, such as halos and highlight clippings. In Gu et al [34], the fused gradient field is derived from the structure tensor of input LDR images based on multi-dimensional Riemannian geometry with a Euclidean metric. Then, the gradient field is modified iteratively with twice averaging filtering and nonlinearly compressing in multi-scales.…”

Section: Introductionmentioning

confidence: 99%