HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning
This work addresses the challenge of cost-effective and accurate HD map learning for autonomous driving systems, representing an incremental improvement over existing methods.
The paper tackles the problem of inaccurate road feature extraction and view transformation in HD map construction from surround-view images by introducing HeightMapNet, which establishes a dynamic relationship between image features and road surface height distributions, achieving exceptional results on nuScenes and Argoverse 2 datasets and outperforming widely recognized approaches.
Recent advances in high-definition (HD) map construction from surround-view images have highlighted their cost-effectiveness in deployment. However, prevailing techniques often fall short in accurately extracting and utilizing road features, as well as in the implementation of view transformation. In response, we introduce HeightMapNet, a novel framework that establishes a dynamic relationship between image features and road surface height distributions. By integrating height priors, our approach refines the accuracy of Bird's-Eye-View (BEV) features beyond conventional methods. HeightMapNet also introduces a foreground-background separation network that sharply distinguishes between critical road elements and extraneous background components, enabling precise focus on detailed road micro-features. Additionally, our method leverages multi-scale features within the BEV space, optimally utilizing spatial geometric information to boost model performance. HeightMapNet has shown exceptional results on the challenging nuScenes and Argoverse 2 datasets, outperforming several widely recognized approaches. The code will be available at \url{https://github.com/adasfag/HeightMapNet/}.