We introduce FPConv, a novel surface-style convolution operator designed for
3D point cloud analysis. Unlike previous methods, FPConv doesn't require
transforming to intermediate representation like 3D grid or graph and directly
works on surface geometry of point cloud. To be more specific, for each point,
FPConv performs a local flattening by automatically learning a weight map to
softly project surrounding points onto a 2D grid. Regular 2D convolution can
thus be applied for efficient feature learning. FPConv can be easily integrated
into various network architectures for tasks like 3D object classification and
3D scene segmentation, and achieve comparable performance with existing
volumetric-type convolutions. More importantly, our experiments also show that
FPConv can be a complementary of volumetric convolutions and jointly training
them can further boost overall performance into state-of-the-art results.

本研究介绍了 FPConv (一种新的表面卷积算子)，可直接作用于点云的表面几何，无需转换为立体或图形中间表示，并可用于 3D 对象分类和 3D 场景分割等任务中，可与现有的立体型卷积具有可比性，同时也可以是立体型卷积的补充，二者联合训练，可以进一步提高整体性能。