A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image

TL;DR

This paper introduces A2J, an anchor-to-joint regression network that estimates 3D hand and body poses from a single depth image using a novel anchor-based approach with high accuracy and speed.

Contribution

The paper proposes a new anchor-based 3D pose estimation method that outperforms existing encoder-decoder and 3D CNN approaches in accuracy and efficiency.

Findings

Achieves high accuracy on multiple datasets

Runs at around 100 FPS on a single GPU

Outperforms state-of-the-art methods in 3D pose estimation

Abstract

For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed. Within A2J, anchor points able to capture global-local spatial context information are densely set on depth image as local regressors for the joints. They contribute to predict the positions of the joints in ensemble way to enhance generalization ability. The proposed 3D articulated pose estimation paradigm is different from the state-of-the-art encoder-decoder based FCN, 3D CNN and point-set based manners. To discover informative anchor points towards certain joint, anchor proposal procedure is also proposed for A2J. Meanwhile 2D CNN (i.e., ResNet-50) is used as backbone network to drive A2J, without using time-consuming 3D convolutional or deconvolutional layers. The experiments on 3 hand datasets and 2 body datasets verify A2J's superiority. Meanwhile, A2J is of high running speed around 100 FPS on single NVIDIA 1080Ti GPU.