论文标题
云变压器：指向云处理任务的通用方法
Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks
论文作者
论文摘要
我们为深点云处理架构提供了一个新的多功能构建块，同样适合各种任务。该基础结合了空间变压器和多视图卷积网络的思想，以及在两个和三维密集网格中的标准卷积层的效率。新块通过多个并行头部运行，而每个头部都会分化各个点的特征表示为低维空间，然后使用密集的卷积来跨点传播信息。然后将单个头部处理的结果组合在一起，从而更新点功能。使用新块，我们构建了用于歧视性（点云分割，点云分类）和生成（点云插入和基于图像的点云重建）任务的体系结构。最终的体系结构实现了这些任务的最新性能，证明了新的块云处理的多功能性。
We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the efficiency of standard convolutional layers in two and three-dimensional dense grids. The new block operates via multiple parallel heads, whereas each head differentiably rasterizes feature representations of individual points into a low-dimensional space, and then uses dense convolution to propagate information across points. The results of the processing of individual heads are then combined together resulting in the update of point features. Using the new block, we build architectures for both discriminative (point cloud segmentation, point cloud classification) and generative (point cloud inpainting and image-based point cloud reconstruction) tasks. The resulting architectures achieve state-of-the-art performance for these tasks, demonstrating the versatility of the new block for point cloud processing.
