用激光与图像联合引导，提升遮挡下3D目标检测的查询初始化效率
ALIGN: Advanced Query Initialization with LiDAR-Image Guidance for Occlusion-Robust 3D Object Detection
- 融合激光点云几何与图像语义，精准定位物体中心
- 在遮挡或密集场景中，最多提升0.9 mAP和1.2 NDS
- 适合做高精度自动驾驶3D检测的工程师或研究者
基于相机与激光雷达输入的查询式3D目标检测方法表现优异，但现有查询初始化策略（如随机采样或鸟瞰图热力图采样）常导致查询使用效率低、准确率下降，尤其在遮挡或密集场景中。为此，我们提出ALIGN（先进查询初始化，结合激光与图像引导），一种鲁棒于遮挡的、面向物体的查询初始化方法。模型包含三个核心组件：(i) 遮挡感知中心估计（OCE），融合激光雷达几何与图像语义以精确估计物体中心；(ii) 自适应邻域采样（ANS），基于激光聚类生成候选物体，并在其周围采样空间与语义对齐的点以补充特征；(iii) 动态查询平衡（DQB），自适应调节前景与背景区域的查询分配。在nuScenes基准上的大量实验表明，ALIGN在多个主流检测器上持续提升性能，尤其在遮挡或密集场景中，最高实现+0.9 mAP和+1.2 NDS的提升。
原文摘要 · Abstract (English)
Recent query-based 3D object detection methods using camera and LiDAR inputs have shown strong performance, but existing query initialization strategies,such as random sampling or BEV heatmap-based sampling, often result in inefficient query usage and reduced accuracy, particularly for occluded or crowded objects. To address this limitation, we propose ALIGN (Advanced query initialization with LiDAR and Image GuidaNce), a novel approach for occlusion-robust, object-aware query initialization. Our model consists of three key components: (i) Occlusion-aware Center Estimation (OCE), which integrates LiDAR geometry and image semantics to estimate object centers accurately (ii) Adaptive Neighbor Sampling (ANS), which generates object candidates from LiDAR clustering and supplements each object by sampling spatially and semantically aligned points around it and (iii) Dynamic Query Balancing (DQB), which adaptively balances queries between foreground and background regions. Our extensive experiments on the nuScenes benchmark demonstrate that ALIGN consistently improves performance across multiple state-of-the-art detectors, achieving gains of up to +0.9 mAP and +1.2 NDS, particularly in challenging scenes with occlusions or dense crowds. Our code will be publicly available upon publication.
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。