BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images.
Thu Nguyen-PhuocChristian RichardtLong MaiYong-Liang YangNiloy J. MitraPublished in: CoRR (2020)
Keyphrases
- d objects
- three dimensional
- cad models
- geometric models
- real world objects
- object recognition
- input image
- surface properties
- multiple images
- image contours
- image data
- range data
- viewpoint
- object parts
- integral imaging
- cad model
- complex scenes
- real objects
- lighting conditions
- feature points
- object models
- image synthesis
- three dimensional objects
- image features
- multi view
- object features
- physically plausible
- geometric constraints
- pose estimation
- range images
- multiple views
- viewing direction
- object classes
- object representation