We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of attention points, our approach learns to locate the best attention points to maximize the performance of a specific task, e.g., point cloud classification. Importantly, we advocate the use of single attention point to facilitate semantic understanding in point feature learning. Specifically, we formulate a new and simple convolution, which combines convolutional features from an input point and its corresponding learned attention point, or LAP, for short. Our attention mechanism can be easily incorporated into state-of-the-art point cloud classification and segmentation networks. Extensive experiments on common benchmarks such as ModelNet40, ShapeNetPart, and S3DIS all demonstrate that our LAP-enabled networks consistently outperform the respective original networks, as well as other competitive alternatives, which employ multiple attention points, either pre-selected or learned under our LAP framework.
翻译:我们提出了一个新的关注机制,以学习点云处理任务的强化点特征,例如分类和分解。与以前曾受过优化预先选定的一组关注点重量的培训的工程不同,我们的方法学会了定位最佳关注点,以最大限度地发挥具体任务(例如点云分类)的绩效。重要的是,我们提倡使用单一关注点,以促进点特征学习中的语义理解。具体地说,我们制定了一个新的简单演进过程,将一个输入点及其相应学习的注意点的连动特征结合起来,或者短期的LAP。我们的注意力机制可以很容易地纳入最先进的点云分类和分解网络。关于模型Net40、ShapeNetPart和S3DIS等共同基准的广泛实验都表明,我们借助LAP的网络始终超越了各自的原始网络,以及其他竞争性的替代方法,这些网络使用了多种关注点,或者是预选的,或者是在我们的LAP框架下学习的。