Shape transformer nets: Generating viewpoint-invariant 3D shapes from a single image.
Jinglun YangYouhua LiLu YangPublished in: J. Vis. Commun. Image Represent. (2021)
Keyphrases
- single image
- viewpoint invariant
- shape recovery
- shape analysis
- shape model
- partially occluded
- shape descriptors
- shape representation
- shape matching
- multiple images
- shape space
- image pairs
- shape prior
- shape from shading
- d scene
- light source
- object class
- smooth surfaces
- surface patches
- super resolution
- shape features
- structured light
- object recognition
- superpixels
- vanishing points
- high resolution