Figure 1. Unsupervised 3D point clouds generated by our tree-GAN for multiple classes (e.g., Motorbike, Laptop, Table, Guitar, Skateboard, Knife, Table, Pistol, and Car from top-left to bottom-right). Our tree-GAN can generate more accurate point clouds than baseline (i.e., r-GAN [1]), and can also produce point clouds for semantic parts of objects, which are denoted by different colors. AbstractIn this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class 3D point cloud generation, a tree-structured graph convolution network (TreeGCN) is introduced as a generator for tree-GAN. Because TreeGCN performs graph convolutions within a tree, it can use ancestor information to boost the representation power for features. To evaluate GANs for 3D point clouds accurately, we develop a novel evaluation metric called Fréchet point cloud distance (FPD). Experimental results demonstrate that the proposed tree-GAN outperforms state-of-the-art GANs in terms of * Authors contributed equally both conventional metrics and FPD, and can generate point clouds for different semantic parts without prior knowledge.