3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
This work addresses the challenge of high-quality 3D point cloud generation for applications in computer vision and graphics, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of generating 3D point clouds by proposing tree-GAN, a novel GAN that uses a tree-structured graph convolution network as a generator, and introduces a new evaluation metric called Frechet point cloud distance. It demonstrates state-of-the-art performance, outperforming existing GANs on conventional metrics and FPD, and can generate point clouds for different semantic parts without prior knowledge.
In 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 Frechet point cloud distance (FPD). Experimental results demonstrate that the proposed tree-GAN outperforms state-of-the-art GANs in terms of both conventional metrics and FPD, and can generate point clouds for different semantic parts without prior knowledge.