Point Cloud Colorization Based on Densely Annotated 3D Shape Dataset

TL;DR

This paper presents DensePoint, a large annotated point cloud dataset, and a GAN-based method for automatic colorization of 3D objects, demonstrating effective boundary-aware coloring results.

Contribution

The paper introduces DensePoint, a comprehensive annotated dataset, and a novel GAN-based approach for point cloud colorization that leverages part annotations.

Findings

GAN can generate plausible colors for point clouds

Clear part boundaries aid in colorization quality

DensePoint dataset supports advanced 3D colorization research

Abstract

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.