BADet: 基于点云的边界感知3D目标检测
BADet: Boundary-Aware 3D Object Detection from Point Clouds
AI总结：
BADet通过构建局部邻域图和轻量级特征聚合模块，提升基于点云的3D目标检测性能。
摘要：
目前，现有最先进的3D目标检测器采用两阶段范式。这些方法通常包括两个步骤：1）利用区域建议网络以自底向上的方式提出少量高质量的建议。2）将所提区域的语义特征进行调整和池化，以总结RoI级别的表示以供进一步细化。需要注意的是，这些RoI级别的表示在步骤2）中被视为独立的无关联条目，当馈送到后续的检测头时。然而，我们观察到步骤1）生成的建议在某种程度上偏离真实情况，以某种概率在局部邻域密集出现。当一个建议由于坐标偏移而大幅放弃其边界信息时，就会产生挑战，而现有网络缺乏相应的信息补偿机制。在本文中，我们提出了BADet用于基于点云的3D目标检测。具体来说，与以往工作不同，我们不将每个建议独立地进行细化，而是将每个建议表示为一个节点，在给定的截断阈值内进行图构造，以局部邻域图的形式关联建议，明确利用对象的边界相关性。此外，我们设计了一个轻量级的区域特征聚合模块，以充分利用体素级、像素级和点级特征，通过扩展感受野来获得更具信息量的RoI级别表示。我们验证了BADet在广泛使用的KITTI数据集和极具挑战性的nuScenes数据集上的有效性。截至2021年4月17日，我们的BADet在KITTI 3D检测排行榜上实现了与现有水平相当的性能，并在KITTI BEV检测排行榜的Car类别Moderate难度上排名第一。源代码可在https://github.com/rui-qian/BADet上获取。
英文摘要：
Currently, existing state-of-the-art 3D object detectors are in two-stage paradigm. These methods typically comprise two steps: 1) Utilize a region proposal network to propose a handful of high-quality proposals in a bottom-up fashion. 2) Resize and pool the semantic features from the proposed regions to summarize RoI-wise representations for further refinement. Note that these RoI-wise representations in step 2) are considered individually as uncorrelated entries when fed to following detection headers. Nevertheless, we observe these proposals generated by step 1) offset from ground truth somehow, emerging in local neighborhood densely with an underlying probability. Challenges arise in the case where a proposal largely forsakes its boundary information due to coordinate offset while existing networks lack corresponding information compensation mechanism. In this paper, we propose $BADet$ for 3D object detection from point clouds. Specifically, instead of refining each proposal independently as previous works do, we represent each proposal as a node for graph construction within a given cut-off threshold, associating proposals in the form of local neighborhood graph, with boundary correlations of an object being explicitly exploited. Besides, we devise a lightweight Region Feature Aggregation Module to fully exploit voxel-wise, pixel-wise, and point-wise features with expanding receptive fields for more informative RoI-wise representations. We validate BADet both on widely used KITTI Dataset and highly challenging nuScenes Dataset. As of Apr. 17th, 2021, our BADet achieves on par performance on KITTI 3D detection leaderboard and ranks $1^{st}$ on $Moderate$ difficulty of $Car$ category on KITTI BEV detection leaderboard. The source code is available at https://github.com/rui-qian/BADet.
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。
