Abstract
Abstract
In this thesis, we introduce a simple and novel mesh convolution operator for learning
dense shape correspondences. Instead of calculating weights between nodes, we
explicitly aggregate node features by serializing neighboring vertices in a fan-shaped
order. Thereafter, we use a fully connected layer to encode vertex features combined
with the local neighborhood information. Finally, we feed the resulting features into
the multi-resolution functional maps module to acquire the final maps. We demonstrate
that our method can be applied to isometric shapes with arbitrary triangulation
and resolution. We evaluate the proposed method on two widely used benchmark
datasets, FAUST and SCAPE. Our results show that our method provides on-par or
better performance than the state-of-the art generalization performance.