Occluded Joints Recovery in 3D Human Pose Estimation based on Distance Matrix
This addresses the challenge of handling occlusions in real-world scenarios for computer vision applications, representing an incremental improvement.
The paper tackles the problem of 3D human pose estimation from single images with occluded joints by using Euclidean distance matrices, proposing two methods that improve accuracy in recovering occluded observations on the Human3.6M dataset.
Albeit the recent progress in single image 3D human pose estimation due to the convolutional neural network, it is still challenging to handle real scenarios such as highly occluded scenes. In this paper, we propose to address the problem of single image 3D human pose estimation with occluded measurements by exploiting the Euclidean distance matrix (EDM). Specifically, we present two approaches based on EDM, which could effectively handle occluded joints in 2D images. The first approach is based on 2D-to-2D distance matrix regression achieved by a simple CNN architecture. The second approach is based on sparse coding along with a learned over-complete dictionary. Experiments on the Human3.6M dataset show the excellent performance of these two approaches in recovering occluded observations and demonstrate the improvements in accuracy for 3D human pose estimation with occluded joints.