用Transformer解码器直接预测3D目标框，提升雷达感知精度。
Leveraging Transformer Decoder for Automotive Radar Object Detection
- 以可学习查询和位置编码构建目标检测集预测框架
- 在RADDet数据集上超越现有纯雷达模型性能
- 无需密集候选框生成与繁琐的NMS调参
本文提出一种基于Transformer的3D雷达目标检测架构，采用新型Transformer解码器作为预测头，直接从雷达特征表示中回归3D边界框和类别分数。为连接多尺度雷达特征与解码器，我们设计轻量级金字塔令牌融合（PTF）模块，将特征金字塔转换为统一的、具备尺度感知能力的令牌序列。通过将检测建模为带可学习对象查询和位置编码的集合预测问题，该设计能够捕捉长程时空相关性和跨特征交互。该方法避免了密集候选框生成以及大量非极大值抑制（NMS）等启发式后处理步骤。我们在RADDet数据集上评估了所提框架，在纯雷达条件下显著优于当前最优基线方法。
原文摘要 · Abstract (English)
In this paper, we present a Transformer-based architecture for 3D radar object detection that uses a novel Transformer Decoder as the prediction head to directly regress 3D bounding boxes and class scores from radar feature representations. To bridge multi-scale radar features and the decoder, we propose Pyramid Token Fusion (PTF), a lightweight module that converts a feature pyramid into a unified, scale-aware token sequence. By formulating detection as a set prediction problem with learnable object queries and positional encodings, our design models long-range spatial-temporal correlations and cross-feature interactions. This approach eliminates dense proposal generation and heuristic post-processing such as extensive non-maximum suppression (NMS) tuning. We evaluate the proposed framework on the RADDet, where it achieves significant improvements over state-of-the-art radar-only baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。