A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds
This addresses the challenge of creating detailed 3D models for applications in computer graphics and vision, though it appears incremental as it builds on existing generative adversarial network methods.
The paper tackles the problem of generating dense and colored 3D point clouds for various object classes in an unsupervised manner, achieving results that mimic 3D data distributions with fine details at multiple resolutions.
In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner. To overcome the difficulty of capturing intricate details at high resolutions, we propose a point transformer that progressively grows the network through the use of graph convolutions. The network is composed of a leaf output layer and an initial set of branches. Every training iteration evolves a point vector into a point cloud of increasing resolution. After a fixed number of iterations, the number of branches is increased by replicating the last branch. Experimental results show that our network is capable of learning and mimicking a 3D data distribution, and produces colored point clouds with fine details at multiple resolutions.