高分辨率人体网格数据集，用于提升3D/4D人体重建精度。
VolHuMe: a High-Resolution Large Scale Dataset of Volumetric Human Meshes
- 64 RGB+32深度相机近距离捕获104人4D扫描数据
- 提供高保真人体网格、手部面部细节与服装分割标注
- 适合研究高精度人体建模与动画生成的团队使用
我们提出VolHuMe，一个基于先进体素工作室、由64个RGB相机和32个深度相机组成的高质量4D人体扫描数据集。该数据集包含104名受试者的个体扫描，提供丰富的真实标签信息，包括SMPL-X参数化模型、高分辨率网格、多视角RGB/深度图像、带骨骼绑定的网格、点云、服装分割以及精细的手部与面部几何结构。与以往依赖全身影像的数据集不同，VolHuMe采用近距离、高分辨率采集方案，有效保留了细微身体部位的细节，显著提升了几何保真度和纹理分辨率。我们在主流3D与4D人体重建方法上对VolHuMe进行基准测试，验证了数据集的质量，并揭示了当前评估体系的局限性。
原文摘要 · Abstract (English)
We introduce VolHuMe, a dataset of high-quality 4D human scans captured with a state-of-the-art volumetric studio using 64 RGB and 32 depth cameras. VolHuMe contains individual captures of 104 subjects and provides extensive ground truth, including SMPL-X, high-resolution meshes, multi-view RGB/depth images, rigged meshes, point clouds, garment segmentation, and detailed hand and facial geometry. Unlike prior datasets that primarily rely on full-body imagery, VolHuMe uses a close-range, high-resolution capture setup that preserves fine-grained body-part details, improving geometric fidelity and texture resolution. We benchmark VolHuMe on state-of-the-art methods across 3D and 4D human reconstruction tasks, showcasing the dataset's quality and exposing the limitations of current evaluation testbeds.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。