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