Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints.
Jinyang YuanBin LiXiangyang XuePublished in: AAAI (2022)
Keyphrases
- unsupervised learning
- viewpoint
- video sequences
- multiple viewpoints
- multiple objects
- d scene
- overlapping views
- machine learning
- single image
- supervised learning
- high dimensional
- dimensionality reduction
- multi view
- multiple views
- training data
- image sequences
- scene understanding
- object models
- scene analysis
- image segmentation
- single viewpoint
- camera viewpoint
- clustering algorithm