Learning to Estimate 3D Hand Pose from Single RGB Images

Code

• github.com/lmb-freiburg/hand3d
  Officialtf★ 0
• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/theerapatkitti/hand_mask_rcnn
  tf★ 0
• github.com/Chenzhoujia/190916-hand3d-CNN-GNN
  tf★ 0
• github.com/theone1984/hand-gesture-ai
  tf★ 0
• github.com/bnestor/second-hand-rl
  tf★ 0
• github.com/ajdillhoff/colorhandpose3d-pytorch
  pytorch★ 0
• github.com/zhong110020/hand3d
  tf★ 0

Abstract

Low-cost consumer depth cameras and deep learning have enabled reasonable 3D hand pose estimation from single depth images. In this paper, we present an approach that estimates 3D hand pose from regular RGB images. This task has far more ambiguities due to the missing depth information. To this end, we propose a deep network that learns a network-implicit 3D articulation prior. Together with detected keypoints in the images, this network yields good estimates of the 3D pose. We introduce a large scale 3D hand pose dataset based on synthetic hand models for training the involved networks. Experiments on a variety of test sets, including one on sign language recognition, demonstrate the feasibility of 3D hand pose estimation on single color images.

Tasks

Reproductions