EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection
This work addresses the problem of improving performance and robustness in 3D object detection for autonomous driving and robotics, with incremental advancements in fusion techniques.
The paper tackles multi-modal 3D object detection by proposing EPNet++ with a Cascade Bi-directional Fusion module and Multi-Modal Consistency loss, achieving state-of-the-art results on KITTI, JRDB, and SUN-RGBD datasets and outperforming existing methods in sparse point cloud scenarios.
Recently, fusing the LiDAR point cloud and camera image to improve the performance and robustness of 3D object detection has received more and more attention, as these two modalities naturally possess strong complementarity. In this paper, we propose EPNet++ for multi-modal 3D object detection by introducing a novel Cascade Bi-directional Fusion~(CB-Fusion) module and a Multi-Modal Consistency~(MC) loss. More concretely, the proposed CB-Fusion module enhances point features with plentiful semantic information absorbed from the image features in a cascade bi-directional interaction fusion manner, leading to more powerful and discriminative feature representations. The MC loss explicitly guarantees the consistency between predicted scores from two modalities to obtain more comprehensive and reliable confidence scores. The experimental results on the KITTI, JRDB and SUN-RGBD datasets demonstrate the superiority of EPNet++ over the state-of-the-art methods. Besides, we emphasize a critical but easily overlooked problem, which is to explore the performance and robustness of a 3D detector in a sparser scene. Extensive experiments present that EPNet++ outperforms the existing SOTA methods with remarkable margins in highly sparse point cloud cases, which might be an available direction to reduce the expensive cost of LiDAR sensors. Code is available at: https://github.com/happinesslz/EPNetV2.