VolHuMe: a High-Resolution Large Scale Dataset of Volumetric Human Meshes
For researchers in 3D/4D human reconstruction, VolHuMe offers a high-quality dataset with fine-grained body-part details that exposes shortcomings of existing benchmarks.
VolHuMe is a high-resolution 4D human scan dataset with 104 subjects captured using 64 RGB and 32 depth cameras, providing extensive ground truth including SMPL-X, high-resolution meshes, and garment segmentation. Benchmarking on state-of-the-art methods reveals limitations in current evaluation testbeds.
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.