A transformer-based lane detection framework with sparse anchor mechanism that generates dynamic anchors from position-aware lane queries and angle queries, achieving competitive performance with fewer computational costs compared to state-of-the-art methods.
ElasticLaneNet is an efficient end-to-end lane detection framework that models lanes as zero-contours on a flexibly shaped Elastic Lane Map (ELM), guided by an elastic interaction energy-loss function to overcome challenges of weak lane features and complex geometric structures.
A novel deep learning-based label assignment approach, named MatchNet, is introduced to enhance the performance of state-of-the-art lane detection models, particularly in scenarios involving curved lanes.