用图注意力网络提升雷达目标检测，显著改善稀疏点云下的感知精度。
Graph Query Networks for Object Detection with Automotive Radar
- 将雷达点云建模为图，通过图查询动态关注鸟瞰图区域。
- 在NuScenes上相对mAP提升53%，比最强基线高8.2%。
- 适合自动驾驶中雷达感知场景，尤其对点云稀疏问题敏感的系统。
基于3D雷达的目标检测对实现汽车全方位感知至关重要，但雷达长波长导致反射点稀疏且分布不规则，给传统的网格和序列型卷积与变压器检测器带来挑战。本文提出图查询网络（GQN），一种基于注意力机制的框架，将雷达感知到的对象建模为图，以提取个性化的关联与上下文特征。GQN引入图查询的新概念，在鸟瞰图空间中动态关注，构建对象特定图，并通过两个新模块处理：用于关系推理的EdgeFocus和用于上下文聚合的DeepContext Pooling。在NuScenes数据集上，GQN相对mAP提升最高达53%，其中相比最强的先前雷达方法提升8.2%，同时将峰值图构建开销降低80%，仅需适度的浮点运算成本。
原文摘要 · Abstract (English)
Object detection with 3D radar is essential for 360-degree automotive perception, but radar's long wavelengths produce sparse and irregular reflections that challenge traditional grid and sequence-based convolutional and transformer detectors. This paper introduces Graph Query Networks (GQN), an attention-based framework that models objects sensed by radar as graphs, to extract individualized relational and contextual features. GQN employs a novel concept of graph queries to dynamically attend over the bird's-eye view (BEV) space, constructing object-specific graphs processed by two novel modules: EdgeFocus for relational reasoning and DeepContext Pooling for contextual aggregation. On the NuScenes dataset, GQN improves relative mAP by up to +53%, including a +8.2% gain over the strongest prior radar method, while reducing peak graph construction overhead by 80% with moderate FLOPs cost.
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。