11 datasets found

Real-time geometry, albedo, and motion reconstruction using a single RGB-D camera

Performance capture from sparse multi-view video

MonoHuman: Animatable Human Neural Field from Monocular Video

The AIST dataset, which consists of dance videos of 30 human subjects captured from 9 cameras.

The dataset used for training and testing the Neural Human Performer model, which consists of free-viewpoint videos of human performers captured from sparse multi-view cameras.

The dataset used for training and testing the proposed TetraTSDF model for 3D human reconstruction from a single image with a tetrahedral outer shell.

A dataset for human performance capture using a single RGB-D camera.

A dataset for human performance capture using weak supervision.

The dataset used for testing and evaluation of the volumetric performance capture system.

The dataset used for volumetric performance capture and rendering from a single RGB camera.

HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs