While often used for monocular (single-camera) reconstruction research, it provides ground truth for 3D human body shapes.
The paper establishes a benchmark for reconstructing the 3D shape and pose of multiple people from monocular video sequences. 090622_001-1pon.mp4
The file name 090622_001-1pon.mp4 follows the dataset's standard indexing, where 090622 typically refers to the capture date or session ID, and 001 identifies the specific subject or sequence. 090622_001-1pon.mp4