The recent success of neural networks enables a better interpretation of 3D
point clouds, but processing a large-scale 3D scene remains a challenging
problem. Most current approaches divide a large-scale scene into small regions
and combine the local predictions together. However, this scheme inevitably
involves additional stages for pre- and post-processing and may also degrade
the final output due to predictions in a local perspective. This paper
introduces Fast Point Transformer that consists of a new lightweight
self-attention layer. Our approach encodes continuous 3D coordinates, and the
voxel hashing-based architecture boosts computational efficiency. The proposed
method is demonstrated with 3D semantic segmentation and 3D detection. The
accuracy of our approach is competitive to the best voxel-based method, and our
network achieves 129 times faster inference time than the state-of-the-art,
Point Transformer, with a reasonable accuracy trade-off in 3D semantic
segmentation on S3DIS dataset.

本文介绍了一种基于 Fast Point Transformer 的新型轻量级自我关注层的方法，用于对大型 3D 场景进行处理和提高计算效率，并应用于 3D 语义分割和 3D 检测，具有与基于体素的最佳方法相竞争的准确性和比 Point Transformer 更快的推理时间。