coupled with performing clustering anal- ysis on shallow vector representations of 3D models (FD-3D) [136].Following this, 2D images containing 3D voxel in- 15 Figure 13. Architectural 3D forms refinement Data Transformation Approach Paper & Methodology generate FD-3D 3D-GAN [135] classify 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 Architectural plasticity: the aesthetics of neural sampling. Architectural Design, 92(3):86–93, 2022. [136] Michael Hasey, Jinmo Rhee, and Daniel Cardoso Llach. Form data as a resource in architectural analysis:

V lil4 面 2)- i 疆旗 C1 i[S 试件信息 预警信息 1 ⅢII □136 Qt1mI ml a104 Q5 anD 试件数里 首Ⅲ入 M 所计负型 UT 期 UT 部口 -1 阳志造