PriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors

TL;DR

PriorMapNet introduces priors into online HD map construction, improving stability and performance by using a PPS-Decoder, PF-Encoder, and DMD cross-attention, achieving state-of-the-art results on nuScenes and Argoverse2.

Contribution

It presents a novel framework that incorporates position and structure priors into the map construction process, enhancing stability and accuracy.

Findings

Achieves state-of-the-art performance on nuScenes and Argoverse2 datasets.

Improves matching stability between predictions and ground truth.

Enhances image-to-BEV transformation with BEV feature priors.

Abstract

Online vectorized High-Definition (HD) map construction is crucial for subsequent prediction and planning tasks in autonomous driving. Following MapTR paradigm, recent works have made noteworthy achievements. However, reference points are randomly initialized in mainstream methods, leading to unstable matching between predictions and ground truth. To address this issue, we introduce PriorMapNet to enhance online vectorized HD map construction with priors. We propose the PPS-Decoder, which provides reference points with position and structure priors. Fitted from the map elements in the dataset, prior reference points lower the learning difficulty and achieve stable matching. Furthermore, we propose the PF-Encoder to enhance the image-to-BEV transformation with BEV feature priors. Besides, we propose the DMD cross-attention, which decouples cross-attention along multi-scale and multi-sample respectively to achieve efficiency. Our proposed PriorMapNet achieves state-of-the-art performance in the online vectorized HD map construction task on nuScenes and Argoverse2 datasets. The code will be released publicly soon.