SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks Fabian B. Fuchs

We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point clouds and graphs, which is equivariant under continuous 3D roto-translations. Equivariance is important to ensure stable and predictable performance in the presence of nuisance transformations of the data input.