Multi-focus image fusion with dense SIFT

By Yu Liu, Shuping Liu, Zengfu Wang. Information Fusion, 2015

464 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/3aad268ac502a62abcbddc8cd7b6ca3ae35413c0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Jiayi Ma
2. Junjun Jiang
3. Yu Liu
4. Han Xu
5. Xun Chen
6. Xiaojie Guo
7. Zengfu Wang
8. Haitao Yin

In Media Technology

1. Jiayi Ma
2. Hui Li
3. Han Xu
4. Xiaojun Wu
5. Junjun Jiang
6. Linfeng Tang
7. Xiaojie Guo
8. Yu Liu

Citations in the corpus

• FusionDN: A Unified Densely Connected Network for Image Fusion (2020, background): “…(Liu and Wang 2015), GBM (Paul, Sevcenco, and Agathoklis 2016), Deepfuse (Prab-hakar, Srikar, and Babu 2017) and FLER (Yang et al. 2018) for multi-exposure fusion, MSTSR (Liu, Liu, and Wang 2015a), DSIFT (Liu, Liu, and Wang 2015b), GBM, CNN (Liu et al. 2017b) and DenseFuse for multi-focus fusion.”
• Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation (2020, unknown): “Based on the scale-invariant feature transform (SIFT), Yu et al. proposed that local image features such as SIFT can be used for image fusion [220] .”
• U2Fusion: A Unified Unsupervised Image Fusion Network (2020, methodology): “…away from the framework, such as the method based on gradient transfer and total variation minimization for VIS-IR image fusion [19], the multi-exposure image fusion method by optimizing a structural similarity index [20], and the method based on dense SIFT for multi-focus image fusion [21], etc .”
• SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer (2022, background): “They also introduced the local feature descriptor ( i.e. , Dense SIFT) into the multi-focus image fusion task to perform activity level measurement and match the misregistered pixels between different source images [40].”
• Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “Liu et al. (2015a) developed a consensus constraint to prune outliers and verified the superiority of their methods for loop closure detection.”
• Pixel-level image fusion: A survey of the state of the art (2017, background): “In order to solve this problem, mutli-focus image fusion merges multiple images of the same scene but with different focus points to create an all-in-focus fused image[53, 68].”
• Image Fusion With Convolutional Sparse Representation (2016, background): “to fusion tasks in which the source images are obtained from the same type of sensors, such as multifocus fusion [3], [5]–[7], [10] and multiexposure fusion [4], [8], [9].”
• Multi-focus image fusion with a deep convolutional neural network (2017, methodology): “…many recently proposed multi-focus image fusion methods are inclined to employ some advanced post-processing techniques, such as the image matting technique used in [26] , the feature matching approach employed in [29] and the Markov Random Field (MRF)-based regularization method applied in [30] .”