论文标题
Center3D：基于中心的单眼3D对象检测具有关节深度理解
Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding
论文作者
论文摘要
只有单眼RGB图像，将对象定位在3D空间中及其相关的3D属性。在透视投影期间，深度信息的丢失使情况更加复杂。我们介绍了一种无锚固方法的Center3D，仅使用单眼RGB图像有效地估算3D位置和深度。通过利用2D和3D中心之间的差异，我们能够始终如一地估计深度。 Center3D使用分类和回归的组合来比单独使用每种方法更强大地了解隐藏的深度信息。我们的方法采用了两种联合方法：（1）盖子：一种分类为主的方法，其顺序线性增加离散化。 （2）Dephoint：以回归为主导的方法，具有多个特征的转换，以进行深度估计。在KITTI数据集上对中等对象进行评估，Center3D将BEV中的AP从$ 29.7 \％$ $提高到$ 42.8 \％$ $，而3D的AP从$ 18.6 \％\％\％\％\％\％$ $ $ 39.1 \％\％$。与最先进的探测器相比，Center3D在实时单眼检测中取得了最佳的速度准确性权衡。
Localizing objects in 3D space and understanding their associated 3D properties is challenging given only monocular RGB images. The situation is compounded by the loss of depth information during perspective projection. We present Center3D, a one-stage anchor-free approach, to efficiently estimate 3D location and depth using only monocular RGB images. By exploiting the difference between 2D and 3D centers, we are able to estimate depth consistently. Center3D uses a combination of classification and regression to understand the hidden depth information more robustly than each method alone. Our method employs two joint approaches: (1) LID: a classification-dominated approach with sequential Linear Increasing Discretization. (2) DepJoint: a regression-dominated approach with multiple Eigen's transformations for depth estimation. Evaluating on KITTI dataset for moderate objects, Center3D improved the AP in BEV from $29.7\%$ to $42.8\%$, and the AP in 3D from $18.6\%$ to $39.1\%$. Compared with state-of-the-art detectors, Center3D has achieved the best speed-accuracy trade-off in realtime monocular object detection.
