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 2305.15219cs.CV
收藏

DynStatF:一种用于LiDAR 3D目标检测的高效特征融合策略

DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection

Horizon Robotics(地平线机器人);University of Munich(慕尼黑大学);University of Tübingen(图宾根大学)

Yao Rong, Xiangyu Wei, Tianwei Lin, Yueyu Wang, Enkelejda Kasneci

AI总结:

本文提出DynStaF特征融合策略,通过邻域交叉注意力和动态-静态交互模块融合多帧语义信息与单帧精确位置信息,在nuScenes上显著提升LiDAR 3D检测性能。

摘要:

用多个先前帧增强LiDAR输入可以提供更丰富的语义信息,从而提升3D目标检测的性能。然而,多帧中拥挤的点云可能由于运动模糊和不准确的点投影而损害精确的位置信息。在这项工作中,我们提出了一种新颖的特征融合策略DynStaF(Dynamic-Static Fusion,动态-静态融合),它利用当前单帧(静态分支)的准确位置信息来增强多帧(动态分支)提供的丰富语义信息。为了有效提取和聚合互补特征,DynStaF包含两个模块:邻域交叉注意力(Neighborhood Cross Attention,NCA)和动态-静态交互(Dynamic-Static Interaction,DSI),它们通过双路径架构运行。NCA以静态分支中的特征作为查询(queries),以动态分支中的特征作为键(keys)和值(values)。在计算注意力时,我们解决了点云的稀疏性问题,只考虑邻域位置。NCA在不同特征图尺度上融合两种特征,随后由DSI提供全面的交互。为了分析我们提出的DynStaF策略,我们在nuScenes数据集上进行了大量实验。在测试集上,DynStaF将PointPillars的NDS性能大幅提升,从57.7%提高到61.6%。当与CenterPoint结合时,我们的框架实现了61.0%的mAP和67.7%的NDS,在没有额外技巧的情况下达到了最先进的性能。

英文摘要:

Augmenting LiDAR input with multiple previous frames provides richer semantic information and thus boosts performance in 3D object detection, However, crowded point clouds in multi-frames can hurt the precise position information due to the motion blur and inaccurate point projection. In this work, we propose a novel feature fusion strategy, DynStaF (Dynamic-Static Fusion), which enhances the rich semantic information provided by the multi-frame (dynamic branch) with the accurate location information from the current single-frame (static branch). To effectively extract and aggregate complimentary features, DynStaF contains two modules, Neighborhood Cross Attention (NCA) and Dynamic-Static Interaction (DSI), operating through a dual pathway architecture. NCA takes the features in the static branch as queries and the features in the dynamic branch as keys (values). When computing the attention, we address the sparsity of point clouds and take only neighborhood positions into consideration. NCA fuses two features at different feature map scales, followed by DSI providing the comprehensive interaction. To analyze our proposed strategy DynStaF, we conduct extensive experiments on the nuScenes dataset. On the test set, DynStaF increases the performance of PointPillars in NDS by a large margin from 57.7% to 61.6%. When combined with CenterPoint, our framework achieves 61.0% mAP and 67.7% NDS, leading to state-of-the-art performance without bells and whistles.

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。

↑