Multi-focus Image Fusion: A Benchmark

Zhang, Xingchen

doi:10.48550/arxiv.2005.01116

Cited by 7 publications

(9 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Lytro dataset includes 20 pairs of multi-focus images and the Mffw dataset 13 pairs of multi-focus images from. 32 The quality of the image fusion method can be obtained through several different objective evaluation metrics. A good fusion result should have clear boundaries and no loss of details.…”

Section: Experimental Settingsmentioning

confidence: 99%

Multi-focus image fusion based on gradient tensor HOSVD

Wang

Cao

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

.Multi-focus image fusion is the process of fusing images of the same scene with different focus ranges. However, pixel misclassification and artifacts caused by noise have been unavoidable problems in fusion methods. To overcome this problem, we propose gradient tensor high-order singular value decomposition (HOSVD) to fuse multi-focus images. The eight-direction Sobel gradient operator is used to obtain second-order gradients in different directions. Tensor-based information processing can effectively represent high-dimensional information and extract structural information from multi-focus images. Therefore, second-order gradient matrices of different images are formed into tensors. The gradient tensor of the images is transformed by HOSVD to obtain the core tensor and factor matrixes. The images are better represented by multiplying the core tensor with the factor matrix corresponding to the direction of the image. In the core tensor, the larger singular values represent basic information and the small singular values high-frequency information. The noise generally belongs to high-frequency information, so we select the larger singular values in the core tensor as activity level variables of the image to reduce noise. Experimental results demonstrate that the proposed fusion method can effectively reduce noise effects and achieve state-of-the-art fusion performance in both objective metrics and visual quality.

show abstract

Section: Experimental Settingsmentioning

confidence: 99%

Multi-focus image fusion based on gradient tensor HOSVD

Wang

Cao

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Extensive tests are carried out to show that the suggested method outperforms other picture fusion algorithms in the literature, both intuitively and numerically. X. Zhang et al [12] provide the MFIFB, a multi-focus image fusion benchmark that includes a test set of 105 picture pairings, a code library of 30 MFIF algorithms, and 20 evaluation measures. MFIFB is the first MFIF benchmark, providing a forum for the community to assess MFIF algorithms thoroughly.…”

Section: Hybrid Image Fusion Modelsmentioning

confidence: 99%

A versatile hybrid image fusion model to fuse multispectral image data

Ignatious

El-Sayed

Khan

et al. 2022

Preprint

View full text Add to dashboard Cite

Higher-level autonomous driving necessitates the best possible execution of important moves under all conditions. Most of the accidents in recent years caused by the AVs launched by leading automobile manufacturers are due to inadequate decision-making caused by their poor perceivance of environmental information. In todays, technology-bound scenarios, versatile sensors are used by AVs to collect environmental information. Due to various technical and natural calamities, the environmental information acquired by the sensors may not be complete and clear, due to which the AVs may misinterpret the information in a different context leading to inadequate decision making causing fatal accidents. To overcome this drawback effective preprocessing of raw sensory data is a mandatory task. Pre-processing the sensory data involves two vital tasks namely data cleaning and data fusion. Since the raw sensory data is complex and exhibits multimodal characteristics, more emphasis is given to data preprocessing. Since more innovative models have been proposed for data cleaning, this study focuses on data fusion. In particular, we propose a generic data fusion engine, which classifies different formats of sensory data and fuses them accordingly to improve accuracy. This study proposes a generic framework to fuse the text, image, and audio data. In the first stage of this research, an innovative hybrid model is proposed to fuse multispectral image and video data. Simple and efficient models to extract the salient image features are also proposed. The proposed models are evaluated using various standard metrics with existing popular models. The proposed image fusion model performed better than the other models.

show abstract

“…After the training, we used multiple data sets for testing and comparison, including (1) Lytro data set conforming to the ideal multi-focus image shooting condition [50]. (2) The data set MFFW [51] which has larger defocus diffusion blur range and more information missing. (3) Savic data set [52], the shooting position changes obviously, the information complementary ability is poor, and there are some motion blur.…”

Section: Data Setmentioning

confidence: 99%

“…For decades, various methods have been proposed. Traditional multi-focus image fusion usually uses the method based on transform domain or method based on spatial domain [2]. However, they are more or less ignored some aspects or contain some defects, researchers often cannot get a more perfect fusion results, which is why image fusion still needs to be studied.…”

Section: Introductionmentioning

confidence: 99%

Pseudo‐Siamese residual atrous pyramid network for multi‐focus image fusion

Jiang

Fan

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Depth of field is one of the critical reasons to limit the richness of image information. Usually, in a scene with multiple targets, when the distance between each target and the lens is different, the clear scene image can be get within a certain distance range. This situation restricts the further image processing, such as semantic segmentation, object recognition and 3D reconstruction. Multi‐focus image fusion uses two or more images focused on different targets to fuse scene information, which can solve this problem to a great extent. In general, two or more multi‐focus images can cover almost all near/far targets. The fusion of more than two multi‐focus images can be accomplished by cascading the fusion results of the previous two images and the next image to be processed many times. Therefore, the paper focus on the fusion of two multi‐focus images. Inspired by this, new Pseudo‐Siamese neural network with several residual atrous convolution pyramids with multi‐level perception ability to perceive the multi‐level features and consistency relations of multi‐focus image pairs is proposed, and multi‐layer residual blocks are used to fuse the extracted features. In this process, the residual of the groundtruth and the generated image will be learned. Finally, a fully focused image without blur will be generated. After several ablation experiments and comparison experiments with other methods, the results show that the performance of the method proposed in this paper is state‐of‐the‐art, and overall better than other methods, which are advanced.

show abstract

Multi-focus Image Fusion: A Benchmark

Cited by 7 publications

References 72 publications

Multi-focus image fusion based on gradient tensor HOSVD

Multi-focus image fusion based on gradient tensor HOSVD

A versatile hybrid image fusion model to fuse multispectral image data

Pseudo‐Siamese residual atrous pyramid network for multi‐focus image fusion

Contact Info

Product

Resources

About