Understanding the structure of the homology embedding can thus disclose geometric or topological information from the data.

Moreover, our approach is capable of effectively learning spatial matching priors to resolve further matching ambiguities. We analyze our GOCor module in extensive ablative experiments.

Approximate attention methods have attempted to address this problem by trading off model quality to reduce the compute complexity, but often do not achieve wall-clock speedup. We argue that a missing principle is making attention algorithms IO-aware -- accounting for reads and writes between levels of GPU memory.