Fully Self-Supervised Class Awareness in Dense Object Descriptors
This addresses the problem of improving object manipulation in robotics, such as grasping in clutter, but appears incremental as it builds on existing self-supervised techniques.
The paper tackles the problem of inferring self-supervised dense semantic correspondences between objects in multi-object scenes, resulting in a method that outperforms previous techniques with more robust pixel-to-pixel matches.
We address the problem of inferring self-supervised dense semantic correspondences between objects in multi-object scenes. The method introduces learning of class-aware dense object descriptors by providing either unsupervised discrete labels or confidence in object similarities. We quantitatively and qualitatively show that the introduced method outperforms previous techniques with more robust pixel-to-pixel matches. An example robotic application is also shown~- grasping of objects in clutter based on corresponding points.