TY - GEN
T1 - A2J
T2 - 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
AU - Xiong, Fu
AU - Zhang, Boshen
AU - Xiao, Yang
AU - Cao, Zhiguo
AU - Yu, Taidong
AU - Zhou, Joey Tianyi
AU - Yuan, Junsong
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85081895788
U2 - 10.1109/ICCV.2019.00088
DO - 10.1109/ICCV.2019.00088
M3 - Conference contribution
AN - SCOPUS:85081895788
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 793
EP - 802
BT - Proceedings - 2019 International Conference on Computer Vision, ICCV 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 27 October 2019 through 2 November 2019
ER -