LighTN：面向点云下采样性能-开销权衡的轻量级Transformer网络
LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling
AI总结：
针对点云下采样中Transformer资源开销大的问题，提出轻量级网络LighTN，通过单头自相关模块、下采样损失和前馈缩放机制，在低开销下实现最先进性能。
摘要：
与传统的任务无关的下采样方法相比，面向任务的神经网络在点云下采样范围内展现出更优的性能。近年来，Transformer网络家族在视觉任务中表现出更强大的学习能力。然而，基于Transformer的架构可能消耗过多资源，这对于下采样范围内低开销的任务网络而言通常不值得。本文提出一种新颖的轻量级Transformer网络（LighTN），用于面向任务的点云下采样，作为一种端到端且即插即用的解决方案。在LighTN中，提出了一个单头自相关模块来提取精细的全局上下文特征，其中同时消除了三个投影矩阵以节省资源开销，且对称矩阵的输出满足置换不变性。然后，我们设计了一种新颖的下采样损失函数，以引导LighTN关注关键点云区域，实现更均匀的分布和显著点的覆盖。此外，我们引入了一种前馈网络缩放机制，根据扩展-缩减策略增强LighTN的可学习能力。在分类和配准任务上的大量实验结果表明，LighTN能够在有限资源开销下实现最先进的性能。
英文摘要：
Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range. Recently, Transformer family of networks has shown a more powerful learning capacity in visual tasks. However, Transformer-based architectures potentially consume too many resources which are usually worthless for low overhead task networks in downsampling range. This paper proposes a novel light-weight Transformer network (LighTN) for task-oriented point cloud downsampling, as an end-to-end and plug-and-play solution. In LighTN, a single-head self-correlation module is presented to extract refined global contextual features, where three projection matrices are simultaneously eliminated to save resource overhead, and the output of symmetric matrix satisfies the permutation invariant. Then, we design a novel downsampling loss function to guide LighTN focuses on critical point cloud regions with more uniform distribution and prominent points coverage. Furthermore, We introduce a feed-forward network scaling mechanism to enhance the learnable capacity of LighTN according to the expand-reduce strategy. The result of extensive experiments on classification and registration tasks demonstrates LighTN can achieve state-of-the-art performance with limited resource overhead.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
