V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map.
Gyeongsik MoonJu Yong ChangKyoung Mu LeePublished in: CoRR (2017)
Keyphrases
- depth map
- human pose estimation
- three dimensional
- depth images
- high quality
- depth information
- stereo matching
- multi view
- high resolution
- input image
- gaussian processes
- super resolution
- low resolution
- image sequences
- spatio temporal
- pose estimation
- input data
- body parts
- video data
- human detection
- human pose
- training data