RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors
This work addresses accuracy and generalization limitations in autonomous driving map construction, representing an incremental improvement over existing Transformer-based methods.
The paper tackles the problem of online HD map construction for autonomous driving by proposing RelMap, a framework that models spatial relations and semantic priors, achieving state-of-the-art performance on nuScenes and Argoverse 2 datasets.
Online high-definition (HD) map construction is crucial for scaling autonomous driving systems. While Transformer-based methods have become prevalent in online HD map construction, most existing approaches overlook the inherent spatial dependencies and semantic relationships among map elements, which constrains their accuracy and generalization capabilities. To address this, we propose RelMap, an end-to-end framework that explicitly models both spatial relations and semantic priors to enhance online HD map construction. Specifically, we introduce a Class-aware Spatial Relation Prior, which explicitly encodes relative positional dependencies between map elements using a learnable class-aware relation encoder. Additionally, we design a Mixture-of-Experts-based Semantic Prior, which routes features to class-specific experts based on predicted class probabilities, refining instance feature decoding. RelMap is compatible with both single-frame and temporal perception backbones, achieving state-of-the-art performance on both the nuScenes and Argoverse 2 datasets.