Recent works have revealed the superiority of feature-level fusion for cross-modal 3D object detection, where fine-grained feature propagation from 2D image pixels to 3D LiDAR points has been widely adopted for performance improvement. Still, the potential of heterogeneous feature propagation between 2D and 3D domains has not been fully explored. In this paper, in contrast to existing pixel-to-point feature propagation, we investigate an opposite point-to-pixel direction, allowing point-wise features to flow inversely into the 2D image branch. Thus, when jointly optimizing the 2D and 3D streams, the gradients back-propagated from the 2D image branch can boost the representation ability of the 3D backbone network working on LiDAR point clouds. Then, combining pixel-to-point and point-to-pixel information flow mechanisms, we construct an bidirectional feature propagation framework, dubbed BiProDet. In addition to the architectural design, we also propose normalized local coordinates map estimation, a new 2D auxiliary task for the training of the 2D image branch, which facilitates learning local spatial-aware features from the image modality and implicitly enhances the overall 3D detection performance. Extensive experiments and ablation studies validate the effectiveness of our method. Notably, we rank $\mathbf{1^{\mathrm{st}}}$ on the highly competitive KITTI benchmark on the cyclist class by the time of submission. The source code is available at https://github.com/Eaphan/BiProDet.

翻译：近期研究揭示了特征级融合在跨模态3D目标检测中的优越性，其中从二维图像像素到三维激光雷达点的细粒度特征传播已被广泛用于性能提升。然而，二维与三维域间异质特征传播的潜力尚未被充分挖掘。本文中，与现有像素到点特征传播不同，我们探索了相反的点到像素方向，使点云特征能够反向流入二维图像分支。因此，在联合优化二维与三维流时，从二维图像分支反向传播的梯度可增强基于激光雷达点云的三维骨干网络的表征能力。进而，结合像素到点与点到像素的信息流机制，我们构建了一个双向特征传播框架，命名为BiProDet。除架构设计外，我们还提出了归一化局部坐标图估计，这是一种用于训练二维图像分支的新型二维辅助任务，有助于从图像模态中学习局部空间感知特征，并隐式提升整体三维检测性能。大量实验和消融研究验证了我们方法的有效性。值得注意的是，在提交时，我们在极具竞争力的KITTI基准测试的行人类别中排名第一。源代码已公开于https://github.com/Eaphan/BiProDet。