A Novel Self-Intersection Penalty Term for Statistical Body Shape Models and Its Applications in 3D Pose Estimation

by   Zaiqiang Wu, et al.

Statistical body shape models are widely used in 3D pose estimation due to their low-dimensional parameters representation. However, it is difficult to avoid self-intersection between body parts accurately. Motivated by this fact, we proposed a novel self-intersection penalty term for statistical body shape models applied in 3D pose estimation. To avoid the trouble of computing self-intersection for complex surfaces like the body meshes, the gradient of our proposed self-intersection penalty term is manually derived from the perspective of geometry. First, the self-intersection penalty term is defined as the volume of the self-intersection region. To calculate the partial derivatives with respect to the coordinates of the vertices, we employed detection rays to divide vertices of statistical body shape models into different groups depending on whether the vertex is in the region of self-intersection. Second, the partial derivatives could be easily derived by the normal vectors of neighboring triangles of the vertices. Finally, this penalty term could be applied in gradient-based optimization algorithms to remove the self-intersection of triangular meshes without using any approximation. Qualitative and quantitative evaluations were conducted to demonstrate the effectiveness and generality of our proposed method compared with previous approaches. The experimental results show that our proposed penalty term can avoid self-intersection to exclude unreasonable predictions and improves the accuracy of 3D pose estimation indirectly. Further more, the proposed method could be employed universally in triangular mesh based 3D reconstruction.


page 2

page 9

page 10

page 11

page 12

page 13


Analytical Derivatives for Differentiable Renderer: 3D Pose Estimation by Silhouette Consistency

Differentiable render is widely used in optimization-based 3D reconstruc...

Feature Boosting Network For 3D Pose Estimation

In this paper, a feature boosting network is proposed for estimating 3D ...

A second-order self-adjusting steepness based remapping method for arbitrary quadrilateral meshes

In this paper, based on the idea of self-adjusting steepness based schem...

Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation

We observe that human poses exhibit strong group-wise structural correla...

Unsupervised Shape and Pose Disentanglement for 3D Meshes

Parametric models of humans, faces, hands and animals have been widely u...

Reconstructing NBA Players

Great progress has been made in 3D body pose and shape estimation from a...

Region extraction in mesh intersection

Region extraction is a very common task in both Computer Science and Eng...