Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image.
Denis TomèChris RussellLourdes AgapitoPublished in: CVPR (2017)
Keyphrases
- single image
- deep learning
- deep belief networks
- multiple images
- shape recovery
- wavelet transform
- image pairs
- d scene
- light source
- shape from shading
- pose estimation
- intrinsic images
- super resolution
- partially occluded
- spherical harmonics
- vanishing points
- multiscale
- computer vision
- multiresolution
- restricted boltzmann machine