EMDB contains in-the-wild videos of human activity recorded with a hand-held iPhone. It features reference SMPL body pose and shape parameters, as well as global body root and camera trajectories. The reference 3D poses were obtained by jointly fitting SMPL to 12 body-worn electromagnetic sensors and image data. For the latter we fit a neural implicit avatar model to allow for a dense pixel-wise fitting objective.

EMDB contains:

81 sequences 105 000 frames 10 actors (5 female, 5 male) Global camera trajectories SMPL pose and shape parameters 2D Keypoints

The dataset can be used to evaluate the following tasks:

Camera-relative 3D human pose and shape estimation from monocular videos. Global 3D human pose and shape estimation including camera trajectories from monocular videos. Human motion prediction.

BEDLAM is a large-scale synthetic video dataset designed to train and test algorithms on the task of 3D human pose and shape estimation (HPS). It contains diverse body shapes, skin tones, and motions. The clothing is realistically simulated on the moving bodies using commercial clothing physics simulation.

We propose to develop ESPRIT: an Exercise Sensing and Pose Recovery Inference Tool, in support of NASA's effort in developing crew exercise technologies for astronaut health and fitness. ESPRIT is a single camera system that monitors the exercise activities of the crew, detects markers placed on the body and other image features, recovers 3D kinematic information of the human body pose, and compiles statistical data about the exercise activities. There are two main challenges for motion capture using a single camera: (1) lack of depth information, and (2) partial occlusion of parts of the body. To overcome these challenges, the proposed framework relies on strong priors on human body pose, shape, and motion dynamics to resolve pose ambiguities. Besides marker locations, it extracts other image features that provide additional cues for recovering pose. It combines both discriminative and generative approaches to achieve robust pose estimation and tracking performance.

Human Bodies in the Wild (HBW) is a validation and test set for body shape estimation. It consists of images taken in the wild and ground truth 3D body scans in SMPL-X topology. To create HBW, we collect body scans of 35 participants and register the SMPL-X model to the scans. Further each participant is photographed in various outfits and poses in front of a white background and uploads full-body photos of themselves taken in the wild. The validation and test set images are released. The ground truth shape is only released for the validation set.