收藏切换
Multi-Modal 3D Object Detection Based on Dynamic Scaling Convolution
收藏切换
Wenyu Ji, Zhuang Miao, Qiyang Zhang, Xiaolu Cui, Weixuan Li, Yang Li*
Journal of Computer Research and Development | 2026, 63(8) : 2059 - 2075
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(8): 2059-2075
• Artificial Intelligence •
Multi-Modal 3D Object Detection Based on Dynamic Scaling Convolution
Full
Wenyu Ji, Zhuang Miao, Qiyang Zhang, Xiaolu Cui, Weixuan Li, Yang Li*
Affiliations
  • College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007
  • born in 2002. Master candidate. His main research interests include deep learning and computer vision

    born in 1976. PhD, professor. Member of CCF. His main research interests include artificial intelligence, pattern recognition, and computer vision

    born in 1998. PhD candidate. His main research interests include information security and object detection

    born in 2002. Master candidate. Her main research interests include computer vision and vehicle re-identification

    born in 2003. Master candidate. Her main research interests include artificial intelligence and computer vision

    born in 1984. PhD, associate professor. Senior member of CCF. His main research interests include computer vision, deep learning, and image retrieval

About Author:

born in 2002. Master candidate. His main research interests include deep learning and computer vision

born in 1976. PhD, professor. Member of CCF. His main research interests include artificial intelligence, pattern recognition, and computer vision

born in 1998. PhD candidate. His main research interests include information security and object detection

born in 2002. Master candidate. Her main research interests include computer vision and vehicle re-identification

born in 2003. Master candidate. Her main research interests include artificial intelligence and computer vision

born in 1984. PhD, associate professor. Senior member of CCF. His main research interests include computer vision, deep learning, and image retrieval

Published: 2026-08-01 doi: 10.7544/issn1000-1239.202550676
Outline
收藏切换

Multi-modal 3D object detection is a pivotal task in autonomous driving and environment perception. It achieves accurate localization and recognition of objects in 3D space by integrating data from multiple sensors, such as LiDAR (light detection and ranging) point clouds and camera images. To address the common challenges of large scale variations and insufficient multi-scale feature extraction in existing methods, we propose a multi-modal 3D object detection method based on dynamic scaling convolution. For this method, we design a dual-branch multi-modal fusion architecture, which consists of a VoxelNet-based 3D backbone and a novel dynamic scaling network. The two branches collaboratively process LiDAR point clouds and image-derived virtual point clouds to achieve cross-modal feature alignment and adaptive fusion. The core of the dynamic scaling network is a dynamic scaling module, which integrates 3D and 2D dynamic scaling convolution operators specifically tailored for multi-modal feature processing. This module adaptively adjusts the sampling locations and the number of valid sampling points within the receptive fields of 3D and 2D branches, thus effectively capturing structural and semantic variations of multi-scale objects. Extensive experiments on two benchmark datasets demonstrate the proposed method outperforms more than ten prevailing methods in terms of AP (average precision). Specifically, it achieves mAP3D (3D mean average precision) scores of 86.87%, 46.68%, and 68.39% for the car, pedestrian, and cyclist categories on KITTI test set, and achieves a mAP (mean average precision) of 71.8% on nuScenes test set. These results demonstrate the superior detection performance and strong generalization ability of the proposed method for multi-modal 3D object detection tasks.

autonomous driving  /  LiDAR point cloud  /  camera image  /  multi-modal fusion  /  3D object detection
纪文宇, 苗壮, 张启阳, 崔小璐, 李唯暄, 李阳. 基于动态缩放卷积的多模态3D目标检测. 计算机研究与发展, 2026 , 63 (8) : 2059 -2075 . DOI: 10.7544/issn1000-1239.202550676
Wenyu Ji, Zhuang Miao, Qiyang Zhang, Xiaolu Cui, Weixuan Li, Yang Li. Multi-Modal 3D Object Detection Based on Dynamic Scaling Convolution[J]. Journal of Computer Research and Development, 2026 , 63 (8) : 2059 -2075 . DOI: 10.7544/issn1000-1239.202550676
Year 2026 volume 63 Issue 8
118
58
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550676
  • Receive Date:2025-09-21
  • Online Date:2026-11-17
  • Published:2026-08-01
Article Data
Affiliations
History
  • Received:2025-09-21
  • Revised:2026-04-13
  • Accepted:2026-04-30
Affiliations
    College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550676
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT