UVG-CWI-DQPC: Dual-Quality Point Cloud Dataset for Volumetric Video Applications

Volumetric video is a key enabler of immersive extended reality experiences and is often represented using point clouds for their structural simplicity. However, capturing volumetric content through multi-view acquisition and depth sensing poses many challenges, such as occlusions and depth mismatches. To foster research in this field, we introduce a unique dual-quality point cloud dataset, named UVG-CWI-DQPC, which is designed to support the development of point cloud enhancement, compression, and quality assessment. Our dataset includes 12 dynamic sequences captured simultaneously by: 1) a high-end capture system producing high-fidelity point clouds with extensive processing; and 2) a consumer-grade capture system relying on affordable RGB-D cameras, lightweight processing, and open-source tools. For each sequence, our dataset provides ground-truth point clouds from the high-end capture system and raw RGB-D footage from the consumer-grade capture system, along with calibration data and tools for point cloud generation. This dual-quality setup enables direct comparison and benchmarking of algorithms for densification, occlusion removal, registration, and quality enhancement. Our dataset is publicly available under a permissive license to support reproducible research and standardization work in Moving Picture Experts Group and 3rd Generation Partnership Project.

体视频（Volumetric video）是沉浸式扩展现实（extended reality）体验的核心赋能技术，常采用点云（point cloud）作为其表示形式，因其结构简洁直观。然而，通过多视图采集（multi-view acquisition）与深度感知（depth sensing）捕获体视频内容时，会面临诸多挑战，例如遮挡（occlusion）与深度失配（depth mismatch）等问题。为推动该领域的研究，我们推出了一款独特的双质量点云数据集（dual-quality point cloud dataset），命名为UVG-CWI-DQPC，旨在支撑点云增强、压缩与质量评估相关技术的研发。本数据集包含12组动态序列，均由两套采集系统同步捕获：1）高端采集系统，经深度处理后可生成高保真（high-fidelity）点云；2）消费级（consumer-grade）采集系统，依托经济型RGB-D相机（RGB-D camera）、轻量处理流程与开源工具完成采集。针对每一组序列，本数据集均提供高端采集系统产出的真值点云（ground-truth point cloud）、消费级采集系统的原始RGB-D影像（raw RGB-D footage），以及点云生成所需的校准数据（calibration data）与配套工具。这种双质量采集设置，可直接用于对点云致密化、遮挡去除、配准与质量增强相关算法进行对比与基准测试。本数据集采用宽松许可协议（permissive license）公开发布，以支撑动态图像专家组（Moving Picture Experts Group, MPEG）与第三代合作伙伴计划（3rd Generation Partnership Project, 3GPP）领域内的可复现研究与标准化工作。