FuseGAN: Learning to Fuse Multi-Focus Image via Conditional Generative Adversarial Network

• Published in: IEEE transactions on multimedia Vol. 21; no. 8; pp. 1982 - 1996
• Main Authors: Guo, Xiaopeng, Nie, Rencan, Cao, Jinde, Zhou, Dongming, Mei, Liye, He, Kangjian
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.08.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Coders; Computer simulation; Computer vision; Conditional generative adversarial network; Conditional random fields; convolutional conditional random fields; Datasets; Gallium nitride; Generative adversarial networks; Generators; Image fusion; Image processing; images-to-image; multi-focus image fusion; Point spread functions; Quantitative analysis; synthesize dataset; Task analysis; Training; Transforms; Visual perception driven algorithms

We study the problem of multi-focus image fusion, where the key challenge is detecting the focused regions accurately among multiple partially focused source images. Inspired by the conditional generative adversarial network (cGAN) to image-to-image task, we propose a novel FuseGAN to fulfill the im...