SparseMeXT Unlocking the Potential of Sparse Representations for HD Map Construction

TL;DR

This paper enhances sparse representation techniques for HD map construction, achieving state-of-the-art accuracy and efficiency, and demonstrating that sparse methods can surpass dense approaches with proper architectural and algorithmic improvements.

Contribution

The authors introduce a specialized network architecture, a sparse-dense segmentation auxiliary task, and a denoising module guided by physical priors, significantly improving sparse HD map construction.

Findings

SparseMeXt-Tiny achieves 55.5% mAP at 32 fps.

SparseMeXt-Base attains 65.2% mAP.

SparseMeXt-Large reaches 68.9% mAP at over 20 fps.

Abstract

Recent advancements in high-definition \emph{HD} map construction have demonstrated the effectiveness of dense representations, which heavily rely on computationally intensive bird's-eye view \emph{BEV} features. While sparse representations offer a more efficient alternative by avoiding dense BEV processing, existing methods often lag behind due to the lack of tailored designs. These limitations have hindered the competitiveness of sparse representations in online HD map construction. In this work, we systematically revisit and enhance sparse representation techniques, identifying key architectural and algorithmic improvements that bridge the gap with--and ultimately surpass--dense approaches. We introduce a dedicated network architecture optimized for sparse map feature extraction, a sparse-dense segmentation auxiliary task to better leverage geometric and semantic cues, and a denoising module guided by physical priors to refine predictions. Through these enhancements, our method achieves state-of-the-art performance on the nuScenes dataset, significantly advancing HD map construction and centerline detection. Specifically, SparseMeXt-Tiny reaches a mean average precision \emph{mAP} of 55.5% at 32 frames per second \emph{fps}, while SparseMeXt-Base attains 65.2% mAP. Scaling the backbone and decoder further, SparseMeXt-Large achieves an mAP of 68.9% at over 20 fps, establishing a new benchmark for sparse representations in HD map construction. These results underscore the untapped potential of sparse methods, challenging the conventional reliance on dense representations and redefining efficiency-performance trade-offs in the field.