TSMC: Time-varying 4D Scene Mesh Compression

摘要

Time-varying scene meshes are a widely used representation for volumetric video, offering immersive six degrees of freedom (6DoF) interaction in virtual environments. However, their significantly larger size presents major challenges for efficient storage, Internet transmission, and real-time streaming. Existing mesh compression standards are not well-suited for complex scene meshes with dynamic content, and no standardized encoding techniques have been widely adopted for this class of data. To address this gap, we propose TSMC, a novel compression framework for 3D time-varying scene mesh sequences. TSMC uses voxel-based analysis to establish temporally stable correspondences, segment static and dynamic regions, and extract volume-tracked reference meshes for dynamic content to support inter-frame prediction. Static backgrounds and reference meshes are compressed using Google Draco, while dynamic displacements are encoded using a combination of the Karhunen-Loève Transform (KLT) and Laplacian coordinates. Extensive experiments demonstrate that at 30 fps and an SSIM of 0.9, TSMC reduces bandwidth usage and decoding time by up to 56.54% and 85.42%, respectively, compared to state-of-the-art mesh compression methods. Our code and dataset are available at https://github.com/SINRG-Lab/TSMC.