Three-dimensional shape reconstruction of objects from a single depth view using deep U-Net convolutional neural network with bottle-neck skip connections.
Edwin Valarezo AñazcoPatricio Rivera LopezTae-Seong KimPublished in: IET Comput. Vis. (2021)
Keyphrases
- shape reconstruction
- three dimensional
- convolutional neural network
- bottle neck
- real objects
- d objects
- cast shadows
- depth map
- shape from shading
- multi view
- multiple views
- shape recognition
- complex objects
- object model
- depth information
- object classes
- multiple objects
- data flow
- light source
- range images
- virtual reality
- face detection
- feature space
- image sequences