.png){kind=icon}
.png){kind=icon}
Return
Towards efficient multi-modal 3D object detection: Homogeneous sparse fuse network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2024.124945.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
LiDAR-only 3D detection methods struggle with the sparsity of point clouds. To overcome this issue, multi- modal methods have been proposed, but their fusion is a challenge due to the heterogeneous representation of images and point clouds. This paper proposes a novel multi-modal framework, Homogeneous Sparse Fusion (HS-Fusion), which generates pseudo point clouds from depth completion. The proposed framework introduces a 3D foreground-aware middle extractor that efficiently extracts high-responding foreground features from sparse point cloud data. This module can be integrated into existing sparse convolutional neural networks. Furthermore, the proposed homogeneous attentive fusion enables cross-modality consistency fusion. Finally, the proposed HS-Fusion can simultaneously combine 2D image features and 3D geometric features of pseudo point clouds using multi-representation feature extraction. The proposed network has been found to attain better performance on the 3D object detection benchmarks. In particular, the proposed model demonstrates a 4.02% improvement in accuracy compared to the pure model. Moreover, its inference speed surpasses that of other models, thus further validating the efficacy of HS-Fusion.
Keywords:
Autonomous driving
3D object detection
Multi-modal
Sparse convolutional networks
Point cloud and image fusion
Homogeneous fusion
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W