4 papers
MAMMA: Markerless & Automatic Multi-Person Motion Action Capture
Hanz Cuevas-Velasquez, Anastasios Yiannakidis, Soyong Shin +7
We present MAMMA, a markerless motion-capture pipeline that accurately recovers SMPL-X parameters from multi-view video of two-person interaction sequences. Traditional motion-capt…
BEDLAM2.0: Synthetic Humans and Cameras in Motion
Joachim Tesch, Giorgio Becherini, Prerana Achar +4
Inferring 3D human motion from video remains a challenging problem with many applications. While traditional methods estimate the human in image coordinates, many applications requ…
Toward Human Understanding with Controllable Synthesis
Hanz Cuevas-Velasquez, Priyanka Patel, Haiwen Feng +1
Training methods to perform robust 3D human pose and shape (HPS) estimation requires diverse training images with accurate ground truth. While BEDLAM demonstrates the potential of…
CameraHMR: Aligning People with Perspective
Priyanka Patel, Michael J. Black
We address the challenge of accurate 3D human pose and shape estimation from monocular images. The key to accuracy and robustness lies in high-quality training data. Existing train…