Adding OSM metadata and RAG-derived lane-width embeddings to SMERF produces modest metric improvements on two OpenLane-V2 intersection scenarios, with the best configuration beating the baseline on all four topology metrics.
ImagineMap: Enhanced HD Map Construction with SD Maps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Track Mapless demands models to process multi-view images and Standard-Definition (SD) maps, outputting lane and traffic element perceptions along with their topological relationships. We propose a novel architecture that integrates SD map priors to improve lane line and area detection performance. Inspired by TopoMLP, our model employs a two-stage structure: perception and reasoning. The downstream topology head uses the output from the upstream detection head, meaning accuracy improvements in detection significantly boost downstream performance.
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Adding OSM metadata and RAG-derived lane-width embeddings to SMERF produces modest metric improvements on two OpenLane-V2 intersection scenarios, with the best configuration beating the baseline on all four topology metrics.