arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.05945cs.CV
收藏

MV2DFusion:利用模态特定目标语义进行多模态三维检测

MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection

Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院)

Zitian Wang, Zehao Huang, Yulu Gao, Naiyan Wang, Si Liu

AI总结:

本文提出MV2DFusion多模态三维检测框架,通过图像与点云查询生成器结合模态特定目标语义,实现稀疏高效融合,在nuScenes和Argoverse2上达到最先进性能,尤其擅长远距离检测。

摘要:

自动驾驶汽车的兴起显著增加了对鲁棒三维目标检测系统的需求。尽管相机和LiDAR传感器各具独特优势——相机提供丰富的纹理信息,LiDAR提供精确的三维空间数据——但依赖单一模态往往会导致性能受限。本文提出了MV2DFusion,一个多模态检测框架,通过先进的基于查询的融合机制整合两种模态的优势。通过引入图像查询生成器以对齐图像特定属性,以及点云查询生成器,MV2DFusion有效结合了模态特定的目标语义,而不会偏向单一模态。随后,稀疏融合过程可以基于有价值的目标语义完成,确保在各种场景下实现高效且准确的目标检测。该框架的灵活性使其能够与任何基于图像和点云的检测器集成,展示了其适应性和未来发展的潜力。在nuScenes和Argoverse2数据集上的广泛评估表明,MV2DFusion实现了最先进的性能,尤其在远距离检测场景中表现出色。

英文摘要:

The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise 3D spatial data--relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generator, MV2DFusion effectively combines modality-specific object semantics without biasing toward one single modality. Then the sparse fusion process can be accomplished based on the valuable object semantics, ensuring efficient and accurate object detection across various scenarios. Our framework's flexibility allows it to integrate with any image and point cloud-based detectors, showcasing its adaptability and potential for future advancements. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that MV2DFusion achieves state-of-the-art performance, particularly excelling in long-range detection scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑