Hand3D: Hand Pose Estimation using 3D Neural Network

04/07/2017
by   Xiaoming Deng, et al.
0

We propose a novel 3D neural network architecture for 3D hand pose estimation from a single depth image. Different from previous works that mostly run on 2D depth image domain and require intermediate or post process to bring in the supervision from 3D space, we convert the depth map to a 3D volumetric representation, and feed it into a 3D convolutional neural network(CNN) to directly produce the pose in 3D requiring no further process. Our system does not require the ground truth reference point for initialization, and our network architecture naturally integrates both local feature and global context in 3D space. To increase the coverage of the hand pose space of the training data, we render synthetic depth image by transferring hand pose from existing real image datasets. We evaluation our algorithm on two public benchmarks and achieve the state-of-the-art performance. The synthetic hand pose dataset will be available.

READ FULL TEXT

page 3

page 5

page 6

page 8

page 9

page 12

page 13

page 14

research
03/03/2019

3D Hand Shape and Pose Estimation from a Single RGB Image

This work addresses a novel and challenging problem of estimating the fu...
research
04/03/2020

HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map

3D hand shape and pose estimation from a single depth map is a new and c...
research
12/05/2018

Point-to-Pose Voting based Hand Pose Estimation using Residual Permutation Equivariant Layer

Recently, 3D input data based hand pose estimation methods have shown st...
research
07/02/2021

HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks

3D hand shape and pose estimation from a single depth map is a new and c...
research
12/06/2018

Learning to Infer the Depth Map of a Hand from its Color Image

We propose the first approach to the problem of inferring the depth map ...
research
07/26/2019

Preterm infants' limb-pose estimation from depth images using convolutional neural networks

Preterm infants' limb-pose estimation is a crucial but challenging task,...
research
09/14/2023

Unleashing the Power of Depth and Pose Estimation Neural Networks by Designing Compatible Endoscopic Images

Deep learning models have witnessed depth and pose estimation framework ...

Please sign up or login with your details

Forgot password? Click here to reset