AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction
By: Thomas Monninger , Md Zafar Anwar , Stanislaw Antol and more
Potential Business Impact:
Helps cars see roads and paths better.
Autonomous driving requires an understanding of the infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned Bird's-Eye View (BEV) encoders are commonly used to combine a set of camera images from multiple views into one joint latent BEV grid. Traditionally, from this latent space, an intermediate raster map is predicted, providing dense spatial supervision but requiring post-processing into the desired vectorized form. More recent models directly derive infrastructure elements as polylines using vectorized map decoders, providing instance-level information. Our approach, Augmentation Map Network (AugMapNet), proposes latent BEV grid augmentation, a novel technique that significantly enhances the latent BEV representation. AugMapNet combines vector decoding and dense spatial supervision more effectively than existing architectures while remaining as straightforward to integrate and as generic as auxiliary supervision. Experiments on nuScenes and Argoverse2 datasets demonstrate significant improvements in vectorized map prediction performance up to 13.3% over the StreamMapNet baseline on 60m range and greater improvements on larger ranges. We confirm transferability by applying our method to another baseline and find similar improvements. A detailed analysis of the latent BEV grid confirms a more structured latent space of AugMapNet and shows the value of our novel concept beyond pure performance improvement. The code will be released soon.
Similar Papers
TS-CGNet: Temporal-Spatial Fusion Meets Centerline-Guided Diffusion for BEV Mapping
CV and Pattern Recognition
Helps self-driving cars see better in bad weather.
Vehicle-to-Infrastructure Collaborative Spatial Perception via Multimodal Large Language Models
Machine Learning (CS)
Helps cars talk to each other better, even in bad weather.
Control Map Distribution using Map Query Bank for Online Map Generation
CV and Pattern Recognition
Makes self-driving cars build maps faster.