arXiv:2608. 09610v1 Announce Type: cross Abstract: Lane detection requires recovering thin, elongated, and frequently occluded lane structures under challenging driving conditions.
By Weize Cai, Yongqi Dong, Zhida Shao, Yichen Liu, Zixin Fu
Lane detection requires recovering thin, elongated, and frequently occluded lane structures under challenging driving conditions. While anchor-based detectors provide efficient candidate generation, their performance is limited by two coupled issues: backbone features often lose structural continuity along partially visible lanes, and classification confidence may decouple from line-level localization quality, allowing inaccurate anchors to persist before non-maximum suppression (NMS).
arXiv:2610.33758v1 Announce Type: new
Abstract: Road infrastructure perception is a fundamental component of autonomous driving, as it recovers the structured road elements that define roadway geomet...
By Guoyang Zhao, Weiqing Qi, Kai Zhang, Zhihai Bi, Tianshuai Hu, Zeying Gong, Dezong Zhao, Jun Ma
The paper introduces the Lane Field, a dense bird‑eye‑view (BEV) geometric representation that captures local lane structure at each spatial location. This representation can be predicted from onboard data or derived from external map priors, and is used in a plug‑and‑play framework that modulates BEV features and guides deformable attention toward lane geometry. Experiments on OpenLane‑V2 demonstrate that these mechanisms consistently improve existing online HD mapping methods, achieving state‑of‑the‑art performance on lane segment perception.
By Andrea Bertogalli, Anthony Dell'Eva, Marcello Ceresini, Federico Pirazzoli, Lorenzo Cipelli, Filippo D'Addeo, Nicola Marinello, Massimo Bertozzi
arXiv:2606. 07366v1 Announce Type: cross Abstract: Self-driving simulations typically rely on data collected in a small number of cities or on hand-authored synthetic scenarios.
By Anurag Ghosh, Francesco Pittaluga, Khiem Vuong, Angela Chen, Juan Alvarez-Padilla, Manmohan Chandraker, Srinivasa Narasimhan
arXiv:2606. 07708v1 Announce Type: cross Abstract: We introduce a dataset and benchmark for cross-view urban traffic perception built from synchronized ego-centric bicycle videos and aerial drone videos recorded at real urban intersections.
By Prakhar Bhardwaj, Simone Weikl, Kilian Mang, Elia Jonas Sandtner