论文标题
使用基于能量的模型的精确3D对象检测
Accurate 3D Object Detection using Energy-Based Models
论文作者
论文摘要
精确的3D对象检测（3DOD）对于通过自动机器人安全导航的复杂环境至关重要。但是，基于稀疏的LiDAR数据，在混乱环境中回归准确的3D边界框是一个极具挑战性的问题。我们通过探索有条件的基于能量的模型（EBM）的最新进展来解决此任务，以进行概率回归。尽管使用EBM进行回归的方法在图像中的2D对象检测上表现出令人印象深刻的性能，但这些技术并不直接适用于3D边界框。因此，在这项工作中，我们为3D边界框设计一个可区分的合并操作员，它是我们EBM网络的核心模块。我们将这种一般方法进一步整合到最新的3D对象检测器SA-SSD中。在KITTI数据集上，我们提出的方法在所有3DD指标上始终优于SA-SSD基线，这表明了基于EBM的回归对高度准确的3DOD的潜力。代码可在https://github.com/fregu856/ebms_3dod上找到。
Accurate 3D object detection (3DOD) is crucial for safe navigation of complex environments by autonomous robots. Regressing accurate 3D bounding boxes in cluttered environments based on sparse LiDAR data is however a highly challenging problem. We address this task by exploring recent advances in conditional energy-based models (EBMs) for probabilistic regression. While methods employing EBMs for regression have demonstrated impressive performance on 2D object detection in images, these techniques are not directly applicable to 3D bounding boxes. In this work, we therefore design a differentiable pooling operator for 3D bounding boxes, serving as the core module of our EBM network. We further integrate this general approach into the state-of-the-art 3D object detector SA-SSD. On the KITTI dataset, our proposed approach consistently outperforms the SA-SSD baseline across all 3DOD metrics, demonstrating the potential of EBM-based regression for highly accurate 3DOD. Code is available at https://github.com/fregu856/ebms_3dod.
