PCVD: A Dataset of Point Cloud Video for Dynamic Human Interaction

Point cloud is widely used in computer vision and augmented reality for representing 3D information of real-world scenes. However, challenges such as noise, incompleteness, and quality variations, particularly in dynamic environments, hinder effective processing and analysis. These issues are further complicated in human activity scenarios due to motion and changing lighting. To address these challenges, this paper introduces a point cloud video dataset PCVD captured with synchronized Azure Kinect cameras, designed to support tasks like denoising, segmentation, and motion recognition in single and multi-person scenes. It provides high-quality depth and color data from diverse real-world scenes with human actions. We compare it with existing datasets, and the results show its superiority in uniformity and completeness, making it ideal for dynamic environments. We also evaluate the state-of-the-art denoising schemes on this dataset to demonstrate the practicality and sophistication of the dataset. The dataset is publicly available at https://github.com/Atlantichan/PCVD-A-Dataset-of-Point-Cloud-Video-for-Dynamic-Human-Interaction.