Training PointNet for human point cloud segmentation with 3D meshes

Three-dimensional (3D) shape estimation of the human body has a growing number of applications in medicine, anthropometry, special effects, and many other fields. Therefore, the demand for the high-quality acquisition of a complete and accurate body model is increasing. In this paper, a short survey of current state-of-the-art solutions is provided. One of the most commonly used approaches is the Shape-from-Silhouette (SfS) method. It is capable of the reconstruction of dynamic and challenging-to-capture objects. This paper proposes a novel approach that extends the conventional voxel-based SfS method with silhouette segmentation—segmented Shape from Silhouette (sSfS). It allows the 3D reconstruction of body segments separately, which provides significantly better human body shape estimation results, especially in concave areas. For validation, a dataset representing the human body in 20 complex poses was created and assessed based on the quality metrics in reference to the ground-truth photogrammetric reconstruction. It appeared that the number of invalid reconstruction voxels for the sSfS method was 1.7 times lower than for the state-of-the-art SfS approach. The root-mean-square (RMS) error of the distance to the reference surface was also 1.22 times lower.

show abstract

Training PointNet for human point cloud segmentation with 3D meshes

Cited by 3 publications

References 2 publications

Monocular Multi-image Scene Restoration

Monocular Multi-image Scene Restoration

Patients Arms Segmentation and Gesture Identification Using Standalone 3-D LiDAR Sensors

sSfS: Segmented Shape from Silhouette Reconstruction of the Human Body

Contact Info

Product

Resources

About