DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation

28 Aug 2017 Markus Oberweger Vincent Lepetit

DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map. Since its publication early 2015, it has been outperformed by several impressive works... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Hand Pose Estimation ICVL Hands DeepPrior++ Average 3D Error 8.1 # 10
Hand Pose Estimation MSRA Hands DeepPrior++ Average 3D Error 9.5 # 7
Hand Pose Estimation NYU Hands DeepPrior++ Average 3D Error 12.3 # 8

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Residual Connection
Skip Connections
Convolution
Convolutions
ResNet
Convolutional Neural Networks