We propose a precise and efficient normal estimation method
that can deal with noise and nonuniform density for unstructured 3D
point clouds. Unlike existing approaches that directly take patches and
ignore the local neighborhood relationships, which make them suscepti-
ble to challenging regions such as sharp edges, we propose to learn graph
convolutional feature representation for normal estimation, which empha-
sizes more local neighborhood geometry and effectively encodes intrinsic
relationships. Additionally, we design a novel adaptive module based on
the attention mechanism to integrate point features with their neigh-
boring features, hence further enhancing the robustness of the proposed
normal estimator against point density variations. To make it more dis-
tinguishable, we introduce a multi-scale architecture in the graph block
to learn richer geometric features. Our method outperforms competitors
with the state-of-the-art accuracy on various benchmark datasets, and
is quite robust against noise, outliers, as well as the density.