EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection

TL;DR

EPNet++ introduces a novel cascade bi-directional fusion module and a multi-modal consistency loss to enhance multi-modal 3D object detection, demonstrating superior performance especially in sparse scenes across multiple datasets.

Contribution

The paper proposes EPNet++, a new multi-modal 3D detection framework with a cascade bi-directional fusion module and a consistency loss, improving feature discrimination and reliability.

Findings

Outperforms state-of-the-art methods on KITTI, JRDB, and SUN-RGBD datasets.

Excels in highly sparse point cloud scenarios, reducing reliance on expensive LiDAR sensors.

Demonstrates robustness and superior accuracy in diverse and sparse environments.

Abstract

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.