FD-3D VAE [136] parameters to FD-3D DCGAN, StyleGAN [137]; 3D-GAN [138] s2 D-3D text to FD-3D 3D-GAN [139] FD-3D 2d to FD-3D 2d StyleGAN, pix2pix [140]; pix2pix, CycleGAN [141] o3 D-3D to FD-3D StyleGAN [142] trained , and according to the textual labels of architectural components (s2 D-3D text to FD-3D) [139]. In terms of basing 2D images to generate refined ar- chitectural 3D models by generative AI, researchers configuration algorithm and a coupled generative adversarial network (cogan). Au- tomation in construction, 139:104234, 2022. [94] Shuyi Huang and Hao Zheng. Morphological regenera- tion of the industrial waterfront