Visible And Infrared Image Fusion Using Encoder-Decoder Network

Abstract

The aim of multispectral image fusion is to combine object or scene features of images with different spectral characteristics to increase the perceptual quality. In this paper, we present a novel learning-based solution to image fusion problem focusing on infrared and visible spectrum images. The proposed solution utilizes only convolution and pooling layers together with a loss function using no-reference quality metrics. The analysis is performed qualitatively and quantitatively on various datasets. The results show better performance than stateof-the-art methods. Also, the size of our network enables real-time performance on embedded devices. Project codes can be found at https://github.com/ferhatcan/ pyFusionSR.

Using Sparse Parts in Fused Information to Enhance Performance in Latent Low-Rank Representation-Based Fusion of Visible and Infrared Images

“…Traditional autoencoders typically employ fully connected layers. Convolutional layers and pooling layers have also been utilized, thus improving feature extraction capabilities and robustness [ 41 , 42 , 43 , 44 , 45 , 46 ]; Transformer-based methods: the Transformer was originally introduced for natural language processing and has demonstrated significant achievements in this domain [ 47 ]. Due to its remarkable long-range modeling capabilities, the Transformer has attracted the attention of researchers in the field of image fusion [ 48 , 49 , 50 , 51 , 52 , 53 ].…”

“…Traditional autoencoders typically employ fully connected layers. Convolutional layers and pooling layers have also been utilized, thus improving feature extraction capabilities and robustness [ 41 , 42 , 43 , 44 , 45 , 46 ];…”

“…Traditional autoencoders typically employ fully connected layers. Convolutional layers and pooling layers have also been utilized, thus improving feature extraction capabilities and robustness [41][42][43][44][45][46]; • Transformer-based methods: the Transformer was originally introduced for natural language processing and has demonstrated significant achievements in this domain [47].…”