S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency.
Mel VeceríkJean-Baptiste RegliOleg SushkovDavid BarkerRugile PevceviciuteThomas RothörlRaia HadsellLourdes AgapitoJonathan ScholzPublished in: CoRL (2020)
Keyphrases
- multi view
- keypoints
- single view
- multiple views
- d objects
- scale invariant
- image matching
- depth map
- three dimensional
- object recognition
- camera calibration
- multi view clustering
- view synthesis
- multi view images
- multiscale
- scale space
- visual words
- image features
- invariant features
- keypoint detection
- semi supervised
- multi view reconstruction
- feature detection
- pose variations
- video sequences
- multi view learning