Direct Dense Pose Estimation

TL;DR

This paper introduces Direct Dense Pose (DDP), a novel, more efficient approach for dense human pose estimation that improves robustness, reduces jitters in video applications, and does not rely on top-down detection methods.

Contribution

The paper proposes DDP, a new dense pose estimation method that predicts instance masks and IUV representations separately, enhancing robustness and efficiency over prior top-down approaches.

Findings

DDP achieves competitive accuracy with existing methods.

DDP is more computationally efficient than previous approaches.

DDP reduces temporal jitters in video sequences.

Abstract

Dense human pose estimation is the problem of learning dense correspondences between RGB images and the surfaces of human bodies, which finds various applications, such as human body reconstruction, human pose transfer, and human action recognition. Prior dense pose estimation methods are all based on Mask R-CNN framework and operate in a top-down manner of first attempting to identify a bounding box for each person and matching dense correspondences in each bounding box. Consequently, these methods lack robustness due to their critical dependence on the Mask R-CNN detection, and the runtime increases drastically as the number of persons in the image increases. We therefore propose a novel alternative method for solving the dense pose estimation problem, called Direct Dense Pose (DDP). DDP first predicts the instance mask and global IUV representation separately and then combines them together. We also propose a simple yet effective 2D temporal-smoothing scheme to alleviate the temporal jitters when dealing with video data. Experiments demonstrate that DDP overcomes the limitations of previous top-down baseline methods and achieves competitive accuracy. In addition, DDP is computationally more efficient than previous dense pose estimation methods, and it reduces jitters when applied to a video sequence, which is a problem plaguing the previous methods.