PVTransformer：用于可扩展3D目标检测的点到体素Transformer
PVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detection
AI总结：
本文提出PVTransformer，用注意力模块替代PointNet池化，解决点云3D检测中的信息瓶颈问题，在Waymo Open Dataset上以76.5 mAPH L2达到最先进性能。
摘要：
针对点云的3D目标检测器通常依赖基于池化的PointNet将稀疏点编码为网格状体素或柱体。在本文中，我们发现常见的PointNet设计引入了信息瓶颈，限制了3D目标检测的精度和可扩展性。为解决这一局限，我们提出PVTransformer：一种基于Transformer的点到体素架构，用于3D检测。我们的核心思想是用注意力模块替代PointNet的池化操作，从而获得更好的点到体素聚合函数。我们的设计既保持了稀疏3D点的置换不变性，又比基于池化的PointNet更具表达能力。实验结果表明，与最新的3D目标检测器相比，我们的PVTransformer取得了显著更好的性能。在广泛使用的Waymo Open Dataset上，我们的PVTransformer达到了最先进的76.5 mAPH L2，比先前最优的SWFormer高出+1.7 mAPH L2。
英文摘要：
3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars. In this paper, we identify that the common PointNet design introduces an information bottleneck that limits 3D object detection accuracy and scalability. To address this limitation, we propose PVTransformer: a transformer-based point-to-voxel architecture for 3D detection. Our key idea is to replace the PointNet pooling operation with an attention module, leading to a better point-to-voxel aggregation function. Our design respects the permutation invariance of sparse 3D points while being more expressive than the pooling-based PointNet. Experimental results show our PVTransformer achieves much better performance compared to the latest 3D object detectors. On the widely used Waymo Open Dataset, our PVTransformer achieves state-of-the-art 76.5 mAPH L2, outperforming the prior art of SWFormer by +1.7 mAPH L2.
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。
