用3D雷达框扩散提升多视角雷达目标检测精度
REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion
- 将2D框扩散扩展到3D雷达空间，实现显式跨视角特征匹配
- 在HIBER和MMVR数据集上分别提升4.22和11.02的AP
- 利用人体接地先验减少参数量，适合复杂室内场景
多视角室内雷达感知因其成本低和隐私风险小而受到关注。现有方法常依赖隐式跨视角雷达特征关联，如RFMask中的提案配对或RETR中的查询-特征交叉注意力，这可能导致特征匹配模糊，在复杂室内场景中性能下降。为此，我们提出REXO（基于3D边界框扩散的多视角雷达目标检测），将DiffusionDet的2D边界框扩散过程提升至3D雷达空间。REXO利用这些带噪的3D边界框引导显式跨视角雷达特征关联，增强跨视角雷达条件去噪过程。通过引入人体接触地面的先验知识，减少了扩散参数数量。在两个公开的室内雷达数据集上评估，本方法在HIBER数据集上超越当前最佳方法4.22 AP，在MMVR数据集上提升11.02 AP。REXO代码已开源：https://github.com/merlresearch/radar-bbox-diffusion。
原文摘要 · Abstract (English)
Multi-view indoor radar perception has drawn attention due to its cost-effectiveness and low privacy risks. Existing methods often rely on {implicit} cross-view radar feature association, such as proposal pairing in RFMask or query-to-feature cross-attention in RETR, which can lead to ambiguous feature matches and degraded detection in complex indoor scenes. To address these limitations, we propose \textbf{REXO} (multi-view Radar object dEtection with 3D bounding boX diffusiOn), which lifts the 2D bounding box (BBox) diffusion process of DiffusionDet into the 3D radar space. REXO utilizes these noisy 3D BBoxes to guide an {explicit} cross-view radar feature association, enhancing the cross-view radar-conditioned denoising process. By accounting for prior knowledge that the person is in contact with the ground, REXO reduces the number of diffusion parameters by determining them from this prior. Evaluated on two open indoor radar datasets, our approach surpasses state-of-the-art methods by a margin of +4.22 AP on the HIBER dataset and +11.02 AP on the MMVR dataset. The REXO implementation is available at https://github.com/merlresearch/radar-bbox-diffusion.
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。