DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing

Point cloud processing is very challenging, as the di verse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape re quires sufficiently contextual semantic information, yet few works devote to this. Here we propose DensePoint, a gen eral architecture to learn densely contextual representation for point cloud processing. Technically, it extends regular grid CNN to irregular point configuration by generalizing a convolution operator, which holds the permutation in variance of points, and achieves efficient inductive learning of local patterns. Architecturally, it finds inspiration from dense connection mode, to repeatedly aggregate multi-level and multi-scale semantics in a deep hierarchy. As a result, densely contextual information along with rich semantics, can be acquired by DensePoint in an organic manner, mak ing it highly effective. Extensive experiments on challenging benchmarks across four tasks, as well as thorough model analysis, verify DensePoint achieves the state of the arts.