通过工作记忆融合提升车载地图构建的时序推理能力
MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction
- 引入工作记忆模块增强多帧历史信息融合能力
- 在公开数据集上实现5.4% mAP提升，最优表现
- 适合自动驾驶高精地图实时构建场景使用
高精地图为自动驾驶系统提供环境信息，是安全路径规划的关键。现有基于单帧输入的方法虽在在线矢量高精地图构建上表现优异，但在复杂场景与遮挡情况下仍存在局限。本文提出MemFusionMap，一种具备增强时序推理能力的新型时序融合模型。具体而言，我们设计了工作记忆融合模块，提升模型对多帧历史信息的存储与推理能力；同时提出新颖的时序重叠热力图，显式提供鸟瞰视图中的时序重叠与车辆轨迹信息。通过融合两项设计，MemFusionMap显著优于现有方法，并保持良好可扩展性。我们在开源基准上进行了广泛评估，相比最先进方法最高提升5.4% mAP。项目主页：https://song-jingyu.github.io/MemFusionMap
原文摘要 · Abstract (English)
High-definition (HD) maps provide environmental information for autonomous driving systems and are essential for safe planning. While existing methods with single-frame input achieve impressive performance for online vectorized HD map construction, they still struggle with complex scenarios and occlusions. We propose MemFusionMap, a novel temporal fusion model with enhanced temporal reasoning capabilities for online HD map construction. Specifically, we contribute a working memory fusion module that improves the model's memory capacity to reason across a history of frames. We also design a novel temporal overlap heatmap to explicitly inform the model about the temporal overlap information and vehicle trajectory in the Bird's Eye View space. By integrating these two designs, MemFusionMap significantly outperforms existing methods while also maintaining a versatile design for scalability. We conduct extensive evaluation on open-source benchmarks and demonstrate a maximum improvement of 5.4% in mAP over state-of-the-art methods. The project page for MemFusionMap is https://song-jingyu.github.io/MemFusionMap
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。