1

Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation
An end-to-end trainable framework that processes large-scale visual data tensors by looking at a fraction of their entries only
Mikhail Usvyatsov, Anastasia Makarova, Rafael Ballester-Ripoll, Maxim Rakhuba, Andreas Krause, Konrad Schindler
Cite PDF Code
Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation
PREDATOR: Registration of 3D Point Clouds with Low Overlap
A model for pairwise point-cloud registration with deep attention to the overlap region.
Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, Konrad Schindler
Cite PDF Code
Indoor Scene Recognition in 3D
Recognising in what type of environment one is located is an important perception task. For instance, for a robot operating in indoors …
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler
Cite PDF Code
Visual recognition in the wild by sampling deep similarity functions
Recognising relevant objects or object states in its environment is a basic capability for an autonomous robot. The dominant approach …
Mikhail Usvyatsov, Konrad Schindler
Cite DOI PDF Code