This paper proposes a deep learning-based method for generating 3D microstructures from a single two-dimensional (2D) image, capable of producing high-quality, realistic 3D images at low cost. In the method, a framework (CEM3DMG) is designed to synthesize 3D images by learning microstructural information from a 2D backscattered electron (BSE) image. Experimental results show that CEM3DMG can generate realistic 3D images of arbitrary size with a resolution of 0.47 $\mu m$ per pixel. Visual observation confirms that the generated 3D images exhibit similar microstructural features to the 2D images, including pores and particles morphology. Furthermore, quantitative analysis reveals that these 3D microstructures closely match the real 2D microstructure in terms of gray level histogram, phase proportions, and pore size distribution.