Point Cloud Colorization Based on Densely Annotated 3D Shape Dataset
This addresses point cloud colorization for 3D vision applications, but is incremental as it builds on existing datasets and GAN methods.
The authors tackled point cloud colorization by creating DensePoint, a densely annotated dataset with over 10,000 objects across 16 categories, each with 40,000 points having RGB and part annotations, and proposed a GAN-based method that generates colors from point clouds alone, showing clear boundaries between object parts in experiments.
This paper introduces DensePoint, a densely sampled and annotated point cloud dataset containing over 10,000 single objects across 16 categories, by merging different kind of information from two existing datasets. Each point cloud in DensePoint contains 40,000 points, and each point is associated with two sorts of information: RGB value and part annotation. In addition, we propose a method for point cloud colorization by utilizing Generative Adversarial Networks (GANs). The network makes it possible to generate colours for point clouds of single objects by only giving the point cloud itself. Experiments on DensePoint show that there exist clear boundaries in point clouds between different parts of an object, suggesting that the proposed network is able to generate reasonably good colours. Our dataset is publicly available on the project page.