Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation.
Sai RajeswarFahim MannanFlorian GolemoJérôme Parent-LévesqueDavid VázquezDerek NowrouzezahraiAaron C. CourvillePublished in: Int. J. Comput. Vis. (2020)
Keyphrases
- d scene
- unsupervised learning
- image based rendering
- object shape
- view dependent
- image data
- input image
- depth map
- object recognition
- three dimensional
- image registration
- image synthesis
- shape descriptors
- scene geometry
- texture mapping
- d mesh
- computer vision
- geometric constraints
- geometric information
- multiple images
- computer graphics
- multi view
- supervised learning
- camera images
- scene representation