SPoVT: Semantic-Prototype Variational Transformer for Dense Point Cloud Semantic Completion

Sheng Yu Huang, Hao-Yu Hsu, Yu-Chiang Frank Wang

Keywords: point cloud, 3D vision, completion

TL;DR: In this paper, we introduce a Semantic-Prototype Variational Transformer (SPoVT) for dense point cloud semantic completion.

Abstract:

Point cloud completion is an active research topic for 3D vision and has been widely
studied in recent years. Instead of directly predicting missing point cloud from
the partial input, we introduce a Semantic-Prototype Variational Transformer
(SPoVT) in this work, which takes both partial point cloud and their semantic
labels as the inputs for semantic point cloud object completion. By observing
and attending at geometry and semantic information as input features, our SPoVT
would derive point cloud features and their semantic prototypes for completion
purposes. As a result, our SPoVT not only performs point cloud completion with
varying resolution, it also allows manipulation of different semantic parts of an
object. Experiments on benchmark datasets would quantitatively and qualitatively
verify the effectiveness and practicality of our proposed model.