MFIF-DWT-CNN: Multi-focus ımage fusion based on discrete wavelet transform with deep convolutional neural network

Semantic-Aware Fusion Network Based on Super-Resolution

“…Among them, the multi-scale transform-based fusion framework is mainly a method to decompose the source image into different scales of information and analyze and fuse them at these scales. Commonly used multi-scale transform methods include wavelet transforms [ 6 , 7 , 8 ] (e.g., discrete wavelets), pyramid transforms [ 9 , 10 , 11 , 12 ] (e.g., gaussian pyramid or laplace pyramid), and methods based on multi-scale geometric analysis [ 13 , 14 , 15 ] (e.g., contour transform or curve transform). These transform methods are able to capture both detailed and global information in an image and have different applicability to different types of images.…”

“…There are more current infrared and visible image fusion methods, but they are mainly categorized into two groups: traditional methods and deep learning (DL)-based methods. Traditional fusion methods are usually based on fusion in the spatial and transform domains [ 5 ], and the image fusion frameworks used mainly include multi-scale transform (MST)-based fusion frameworks [ 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 ], sparse representation (SR)-based fusion frameworks [ 16 , 17 , 18 ], subspace-based fusion frameworks [ 19 , 20 , 21 ], saliency-based fusion frameworks [ 22 ], and hybrid fusion frameworks [ 23 , 24 , 25 ]. And according to the adopted network architecture, the DL-based image fusion methods can be mainly categorized into three groups, which are autoencoders (AE)-based image fusion frameworks [ 26 , 27 , 28 , 29 , 30 ], convolutional neural network (CNN)-based image fusion frameworks [ 31 , 32 , 33 , 34 , 35 , 36 , 37 ] and generative adversarial network-(GAN) based image fusion frameworks [ 38 , 39 , 40 , 41 , 42 , 43 ].…”