Attention-based Point Cloud Edge Sampling
This work addresses point cloud sampling for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackled the problem of point cloud sampling by proposing APES, a non-generative method that captures salient points in point cloud outlines using attention mechanisms, achieving superior performance on benchmark tasks.
Point cloud sampling is a less explored research topic for this data representation. The most commonly used sampling methods are still classical random sampling and farthest point sampling. With the development of neural networks, various methods have been proposed to sample point clouds in a task-based learning manner. However, these methods are mostly generative-based, rather than selecting points directly using mathematical statistics. Inspired by the Canny edge detection algorithm for images and with the help of the attention mechanism, this paper proposes a non-generative Attention-based Point cloud Edge Sampling method (APES), which captures salient points in the point cloud outline. Both qualitative and quantitative experimental results show the superior performance of our sampling method on common benchmark tasks.