Transformers have been recently explored for 3D point cloud understanding
with impressive progress achieved. A large number of points, over 0.1 million,
make the global self-attention infeasible for point cloud data. Thus, most
methods propose to apply the transformer in a local region, e.g., spherical or
cubic window. However, it still contains a large number of Query-Key pairs,
which requires high computational costs. In addition, previous methods usually
learn the query, key, and value using a linear projection without modeling the
local 3D geometric structure. In this paper, we attempt to reduce the costs and
model the local geometry prior by developing a new transformer block, named
ConDaFormer. Technically, ConDaFormer disassembles the cubic window into three
orthogonal 2D planes, leading to fewer points when modeling the attention in a
similar range. The disassembling operation is beneficial to enlarging the range
of attention without increasing the computational complexity, but ignores some
contexts. To provide a remedy, we develop a local structure enhancement
strategy that introduces a depth-wise convolution before and after the
attention. This scheme can also capture the local geometric information. Taking
advantage of these designs, ConDaFormer captures both long-range contextual
information and local priors. The effectiveness is demonstrated by experimental
results on several 3D point cloud understanding benchmarks. Code is available
at this https URL .

将局部几何结构和长范围上下文信息耦合进 ConDaFormer 中，通过将相应的立方体窗口分解为三个正交的 2D 平面，以在类似范围内建模注意力，提高了性能和模型的计算效率。