空 挡 广 告 位 | 空 挡 广 告 位

A Dynamic 3D Point Cloud Dataset for Immersive Applications

Note: We don't have the ability to review paper

PubDate:June 2023

Teams:National Tsing Hua University;National University of Singapore;National Yang Ming Chiao Tung University

Writers:Yuan-Chun Sun,I-Chun Huang,Yuang Shi,Wei Tsang Ooi,Chun-Ying Huang,Cheng-Hsin Hsu

PDF:A Dynamic 3D Point Cloud Dataset for Immersive Applications

Abstract

Motion estimation in a 3D point cloud sequence is a fundamental operation with many applications, including compression, error concealment, and temporal upscaling. While there have been multiple research contributions toward estimating the motion vector of points between frames, there is a lack of a dynamic 3D point cloud dataset with motion ground truth to benchmark against. In this paper, we present an open dynamic 3D point cloud dataset to fill this gap. Our dataset consists of synthetically generated objects with pre-determined motion patterns, allowing us to generate the motion vectors for the points. Our dataset contains nine objects in three categories (shape, avatar, and textile) with different animation patterns. We also provide semantic segmentation of each avatar object in the dataset. Our dataset can be used by researchers who need temporal information across frames. As an example, we present an evaluation of two motion estimation methods using our dataset.

您可能还喜欢...

Paper