Multi-View Adaptive Fusion Network for 3D Object Detection

TL;DR

This paper introduces MVAF-Net, a novel multi-view fusion network for 3D object detection that adaptively combines LiDAR and camera data using attention mechanisms, significantly improving detection accuracy and efficiency.

Contribution

The paper proposes an end-to-end multi-view fusion framework with attentive modules for adaptive feature integration, outperforming existing single-stage and two-stage fusion methods.

Findings

Achieves state-of-the-art performance on KITTI dataset.

Demonstrates effective adaptive fusion of multi-view features.

Balances speed and accuracy in 3D detection.

Abstract

3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving. However, it has been surprisingly difficult to effectively fuse both modalities without information loss and interference. To solve this issue, we propose a single-stage multi-view fusion framework that takes LiDAR bird's-eye view, LiDAR range view and camera view images as inputs for 3D object detection. To effectively fuse multi-view features, we propose an attentive pointwise fusion (APF) module to estimate the importance of the three sources with attention mechanisms that can achieve adaptive fusion of multi-view features in a pointwise manner. Furthermore, an attentive pointwise weighting (APW) module is designed to help the network learn structure information and point feature importance with two extra tasks, namely, foreground classification and center regression, and the predicted foreground probability is used to reweight the point features. We design an end-to-end learnable network named MVAF-Net to integrate these two components. Our evaluations conducted on the KITTI 3D object detection datasets demonstrate that the proposed APF and APW modules offer significant performance gains. Moreover, the proposed MVAF-Net achieves the best performance among all single-stage fusion methods and outperforms most two-stage fusion methods, achieving the best trade-off between speed and accuracy on the KITTI benchmark.