# Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping

## TL;DR

This paper introduces a probabilistic BEV projection method that enhances online HD mapping accuracy by adaptively refining geometric projections with confidence scores, reducing hallucinations and improving generalization.

## Contribution

It proposes a novel probabilistic projection mechanism with confidence scores to improve BEV mapping accuracy and robustness in HD map construction.

## Key findings

- Outperforms state-of-the-art methods on nuScenes and Argoverse2 datasets.
- Achieves better generalization and accuracy, especially at long perception ranges.
- Effectively filters irrelevant scene elements using confidence scores.

## Abstract

Constructing high-definition (HD) maps from sensory input requires accurately mapping the road elements in image space to the Bird's Eye View (BEV) space. The precision of this mapping directly impacts the quality of the final vectorized HD map. Existing HD mapping approaches outsource the projection to standard mapping techniques, such as attention-based ones. However, these methods struggle with accuracy due to generalization problems, often hallucinating non-existent road elements. Our key idea is to start with a geometric mapping based on camera parameters and adapt it to the scene to extract relevant map information from camera images. To implement this, we propose a novel probabilistic projection mechanism with confidence scores to (i) refine the mapping to better align with the scene and (ii) filter out irrelevant elements that should not influence HD map generation. In addition, we improve temporal processing by using confidence scores to selectively accumulate reliable information over time. Experiments on new splits of the nuScenes and Argoverse2 datasets demonstrate improved performance over state-of-the-art approaches, indicating better generalization. The improvements are particularly pronounced on nuScenes and in the challenging long perception range. Our code and model checkpoints are available at https://github.com/Fatih-Erdogan/mapping-like-skeptic .