Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D Network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundary. To solve this issue, we propose an auxiliary corner attention module to enforce the CNN backbone to pay more attention to object boundaries which is effective to obtain more accurate bounding boxes. Besides, our CenterNet3D is Non-Maximum Suppression free which makes it more efficient and simpler. On the KITTI benchmark, our proposed CenterNet3D achieves competitive performance with other one stage anchor-based methods which show the efficacy of our proposed center point representation.

中文翻译：

---

CenterNet3D：用于自动驾驶的无锚物体检测器

从点云中准确快速地检测 3D 对象是自动驾驶中的一项关键任务。现有的单阶段 3D 对象检测方法可以实现实时性能，但是，它们主要是基于锚点的检测器，效率低下并且需要额外的后处理。在本文中，我们消除了锚点，并将对象建模为其边界框的中心点。基于中心点，我们提出了一种无锚点的 CenterNet3D 网络，它可以在没有锚点的情况下执行 3D 对象检测。我们的 CenterNet3D 使用关键点估计来找到中心点并直接回归 3D 边界框。然而，由于点云固有的稀疏性，3D 对象中心点很可能在空白空间中，这使得难以估计准确的边界。为了解决这个问题，我们提出了一个辅助角点注意模块来强制 CNN 主干更多地关注对象边界，这有助于获得更准确的边界框。此外，我们的 CenterNet3D 是无非最大抑制的，这使其更高效、更简单。在 KITTI 基准测试中，我们提出的 CenterNet3D 与其他基于锚点的单阶段方法相比取得了有竞争力的性能，这显示了我们提出的中心点表示的有效性。