Pose2Pose: 3D Positional Pose-Guided 3D Rotational Pose Prediction for Expressive 3D Human Pose and Mesh Estimation
Gyeongsik Moon, Kyoung Mu Lee · arXiv (Cornell University) · 2020
Previous expressive 3D human pose and mesh estimation methods mostly rely on a single image feature vector to predict 3D rotations of human joints (i.e., 3D rotational pose) from an input image. However, the single image feature vector lacks human joint-level features. To resolve the limitation, we present Pose2Pose, a 3D positional pose-guided 3D rotational pose prediction framework for expressive 3D human pose and mesh estimation. Pose2Pose extracts the joint-level features on the position of human joints (i.e., positional pose) using a positional pose-guided pooling, and the joint-level features are used for the 3D rotational pose prediction. Our Pose2Pose is trained in an end-to-end manner and largely outperforms previous expressive methods. The codes will be publicly available.