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

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... (read more)

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Hand Pose Estimation HANDS 2017 A2J Average 3D Error 8.57 # 2
Hand Pose Estimation ICVL Hands A2J Average 3D Error 6.461 # 4
FPS 105.06 # 1
Pose Estimation ITOP front-view A2J Mean mAP 88.0 # 1
Hand Pose Estimation K2HPD A2J PDJ@5mm 76.3 # 1
3D Pose Estimation K2HPD A2J FPS 93.78 # 1
Depth Estimation NYU-Depth V2 A2J mAP 8.61 # 1
Hand Pose Estimation NYU Hands A2J Average 3D Error 8.61 # 3
FPS 105.06 # 1

Methods used in the Paper


METHOD TYPE
Max Pooling
Pooling Operations
Convolution
Convolutions
FCN
Semantic Segmentation Models