[3I4-GS-7a] 画像音声メディア処理：基礎

[3I4-GS-7a-04] Geometric Structure-Aware 3D Point Cloud Generation by Deep Learning

〇Takumi Kimura¹, Takashi Matsubara², Kuniaki Uehara³ (1. Kobe University, 2. Osaka University, 3. Osaka Gakuin University)

Keywords:Point Cloud, Deep Generative Model, Deep Learning

A three-dimensional point cloud is used in a wide range of fields such as robotics and autonomous cars and is becoming popular as a compact representation of an object's surface. Deep generative models for point clouds typically have been adapted to model variations by a map from a ball-like set of latent variables. However, previous approaches have not paid much attention to the topological structure of a point cloud. For this reason, a continuous map cannot express the varying number of holes and intersections. In this paper, we propose a flow-based deep generative model with multiple latent labels. By maximizing the mutual information, a map conditioned by a label is assigned to a continuous subset of a given point cloud, like a chart of a manifold. This enables our proposed model to preserve the topological structure with clear boundaries, while previous approaches tend to suffer from blurs and to fail in generating holes. Experimental results demonstrate that our proposed model achieves the state-of-the-art performance in generation and reconstruction among sampling-based point cloud generators.